Sennur Ulukus

Purbesh Mitra, Sennur Ulukus

Long context reasoning in large language models (LLMs) has demonstrated enhancement of their cognitive capabilities via chain-of-thought (CoT) inference. Training such models is usually done via reinforcement learning with verifiable rewards (RLVR) in reasoning based problems, like math and programming. However, RLVR is limited by several bottlenecks, such as, lack of dense reward, and inadequate sample efficiency. As a result, it requires significant compute resources in post-training phase. To overcome these limitations, in this work, we propose \textbf{Semantic Soft Bootstrapping (SSB)}, a self-distillation technique, in which the same base language model plays the role of both teacher and student, but receives different semantic contexts about the correctness of its outcome at training time. The model is first prompted with a math problem and several rollouts are generated. From them, the correct and most common incorrect response are filtered, and then provided to the model in context to produce a more robust, step-by-step explanation with a verified final answer. This pipeline automatically curates a paired teacher-student training set from raw problem-answer data, without any human intervention. This generation process also produces a sequence of logits, which is what the student model tries to match in the training phase just from the bare question alone. In our experiment, Qwen2.5-3B-Instruct on GSM8K dataset via parameter-efficient fine-tuning. We then tested its accuracy on MATH500, and AIME2024 benchmarks. Our experiments show a jump of 10.6%, and 10% improvements in accuracy, respectively, over group relative policy optimization (GRPO), which is a commonly used RLVR algorithm. Our code is available at https://github.com/purbeshmitra/semantic-soft-bootstrapping, and the model, curated dataset is available at https://huggingface.co/purbeshmitra/semantic-soft-bootstrapping.

Arunabh Srivastava, Sennur Ulukus

We consider a cellular network containing $n$ nodes where nodes within a cell gossip with each other in a fully-connected fashion and a source shares updates with these nodes via a mobile drone. The drone receives source updates and shares them with nodes in the cell where it currently resides. The drone moves between cells according to an underlying continuous-time Markov chain (CTMC). We evaluate the impact of the number of cells $f(n)$, drone speed $λ_m(n)$ and drone dissemination rate $λ_d(n)$ on the information freshness of nodes in the network. We use the version age of information metric to quantify information freshness. We observe that the expected duration between two drone-to-cell service times depends on the stationary distribution of the underlying CTMC and $λ_d(n)$, but not on $λ_m(n)$. However, the version age instability makes high probability analysis for a general underlying CTMC difficult. Therefore, we focus on the fully-connected drone mobility model. Under this model, we uncover a dual-bottleneck, by leveraging stochastic equivalence between drone mobility and drone dissemination speed: the version age is constrained by the slower of these two processes. If $λ_d(n) \gg λ_m(n)$, then the version age scaling of nodes is dominated by the inverse of $λ_m(n)$ and is independent of $λ_d(n)$. If $λ_m(n) \gg λ_d(n)$, then the version age scaling of nodes is dominated by the inverse of $λ_d(n)$ and is independent of $λ_m(n)$.

Yalin E. Sagduyu, Sennur Ulukus, Aylin Yener

Communications systems to date are primarily designed with the goal of reliable transfer of digital sequences (bits). Next generation (NextG) communication systems are beginning to explore shifting this design paradigm to reliably executing a given task such as in task-oriented communications. In this paper, wireless signal classification is considered as the task for the NextG Radio Access Network (RAN), where edge devices collect wireless signals for spectrum awareness and communicate with the NextG base station (gNodeB) that needs to identify the signal label. Edge devices may not have sufficient processing power and may not be trusted to perform the signal classification task, whereas the transfer of signals to the gNodeB may not be feasible due to stringent delay, rate, and energy restrictions. Task-oriented communications is considered by jointly training the transmitter, receiver and classifier functionalities as an encoder-decoder pair for the edge device and the gNodeB. This approach improves the accuracy compared to the separated case of signal transfer followed by classification. Adversarial machine learning poses a major security threat to the use of deep learning for task-oriented communications. A major performance loss is shown when backdoor (Trojan) and adversarial (evasion) attacks target the training and test processes of task-oriented communications.

Yalin E. Sagduyu, Tugba Erpek, Sennur Ulukus et al.

This paper highlights vulnerabilities of deep learning-driven semantic communications to backdoor (Trojan) attacks. Semantic communications aims to convey a desired meaning while transferring information from a transmitter to its receiver. An encoder-decoder pair that is represented by two deep neural networks (DNNs) as part of an autoencoder is trained to reconstruct signals such as images at the receiver by transmitting latent features of small size over a limited number of channel uses. In the meantime, another DNN of a semantic task classifier at the receiver is jointly trained with the autoencoder to check the meaning conveyed to the receiver. The complex decision space of the DNNs makes semantic communications susceptible to adversarial manipulations. In a backdoor (Trojan) attack, the adversary adds triggers to a small portion of training samples and changes the label to a target label. When the transfer of images is considered, the triggers can be added to the images or equivalently to the corresponding transmitted or received signals. In test time, the adversary activates these triggers by providing poisoned samples as input to the encoder (or decoder) of semantic communications. The backdoor attack can effectively change the semantic information transferred for the poisoned input samples to a target meaning. As the performance of semantic communications improves with the signal-to-noise ratio and the number of channel uses, the success of the backdoor attack increases as well. Also, increasing the Trojan ratio in training data makes the attack more successful. In the meantime, the effect of this attack on the unpoisoned input samples remains limited. Overall, this paper shows that the backdoor attack poses a serious threat to semantic communications and presents novel design guidelines to preserve the meaning of transferred information in the presence of backdoor attacks.

Yalin E. Sagduyu, Tugba Erpek, Aylin Yener et al.

This paper explores the integration of deep learning techniques for joint sensing and communications, with an extension to semantic communications. The integrated system comprises a transmitter and receiver operating over a wireless channel, subject to noise and fading. The transmitter employs a deep neural network (DNN), namely an encoder, for joint operations of source coding, channel coding, and modulation, while the receiver utilizes another DNN, namely a decoder, for joint operations of demodulation, channel decoding, and source decoding to reconstruct the data samples. The transmitted signal serves a dual purpose, supporting communication with the receiver and enabling sensing. When a target is present, the reflected signal is received, and another DNN decoder is utilized for sensing. This decoder is responsible for detecting the target's presence and determining its range. All these DNNs, including one encoder and two decoders, undergo joint training through multi-task learning, considering data and channel characteristics. This paper extends to incorporate semantic communications by introducing an additional DNN, another decoder at the receiver, operating as a task classifier. This decoder evaluates the fidelity of label classification for received signals, enhancing the integration of semantics within the communication process. The study presents results based on using the CIFAR-10 as the input data and accounting for channel effects like Additive White Gaussian Noise (AWGN) and Rayleigh fading. The results underscore the effectiveness of multi-task deep learning in achieving high-fidelity joint sensing and semantic communications.

Yalin E. Sagduyu, Tugba Erpek, Aylin Yener et al.

This paper studies task-oriented, otherwise known as goal-oriented, communications, in a setting where a transmitter communicates with multiple receivers, each with its own task to complete on a dataset, e.g., images, available at the transmitter. A multi-task deep learning approach that involves training a common encoder at the transmitter and individual decoders at the receivers is presented for joint optimization of completing multiple tasks and communicating with multiple receivers. By providing efficient resource allocation at the edge of 6G networks, the proposed approach allows the communications system to adapt to varying channel conditions and achieves task-specific objectives while minimizing transmission overhead. Joint training of the encoder and decoders using multi-task learning captures shared information across tasks and optimizes the communication process accordingly. By leveraging the broadcast nature of wireless communications, multi-receiver task-oriented communications (MTOC) reduces the number of transmissions required to complete tasks at different receivers. Performance evaluation conducted on the MNIST, Fashion MNIST, and CIFAR-10 datasets (with image classification considered for different tasks) demonstrates the effectiveness of MTOC in terms of classification accuracy and resource utilization compared to single-task-oriented communication systems.

Yalin E. Sagduyu, Tugba Erpek, Sennur Ulukus et al.

Semantic communications seeks to transfer information from a source while conveying a desired meaning to its destination. We model the transmitter-receiver functionalities as an autoencoder followed by a task classifier that evaluates the meaning of the information conveyed to the receiver. The autoencoder consists of an encoder at the transmitter to jointly model source coding, channel coding, and modulation, and a decoder at the receiver to jointly model demodulation, channel decoding and source decoding. By augmenting the reconstruction loss with a semantic loss, the two deep neural networks (DNNs) of this encoder-decoder pair are interactively trained with the DNN of the semantic task classifier. This approach effectively captures the latent feature space and reliably transfers compressed feature vectors with a small number of channel uses while keeping the semantic loss low. We identify the multi-domain security vulnerabilities of using the DNNs for semantic communications. Based on adversarial machine learning, we introduce test-time (targeted and non-targeted) adversarial attacks on the DNNs by manipulating their inputs at different stages of semantic communications. As a computer vision attack, small perturbations are injected to the images at the input of the transmitter's encoder. As a wireless attack, small perturbations signals are transmitted to interfere with the input of the receiver's decoder. By launching these stealth attacks individually or more effectively in a combined form as a multi-domain attack, we show that it is possible to change the semantics of the transferred information even when the reconstruction loss remains low. These multi-domain adversarial attacks pose as a serious threat to the semantics of information transfer (with larger impact than conventional jamming) and raise the need of defense methods for the safe adoption of semantic communications.

Matin Mortaheb, Cemil Vahapoglu, Sennur Ulukus

Multi-task learning (MTL) is a novel framework to learn several tasks simultaneously with a single shared network where each task has its distinct personalized header network for fine-tuning. MTL can be implemented in federated learning settings as well, in which tasks are distributed across clients. In federated settings, the statistical heterogeneity due to different task complexities and data heterogeneity due to non-iid nature of local datasets can both degrade the learning performance of the system. In addition, tasks can negatively affect each other's learning performance due to negative transference effects. To cope with these challenges, we propose FedGradNorm which uses a dynamic-weighting method to normalize gradient norms in order to balance learning speeds among different tasks. FedGradNorm improves the overall learning performance in a personalized federated learning setting. We provide convergence analysis for FedGradNorm by showing that it has an exponential convergence rate. We also conduct experiments on multi-task facial landmark (MTFL) and wireless communication system dataset (RadComDynamic). The experimental results show that our framework can achieve faster training performance compared to equal-weighting strategy. In addition to improving training speed, FedGradNorm also compensates for the imbalanced datasets among clients.

Yalin E. Sagduyu, Sennur Ulukus, Aylin Yener

This paper studies the notion of age in task-oriented communications that aims to execute a task at a receiver utilizing the data at its transmitter. The transmitter-receiver operations are modeled as an encoder-decoder pair that is jointly trained while considering channel effects. The encoder converts data samples into feature vectors of small dimension and transmits them with a small number of channel uses thereby reducing the number of transmissions and latency. Instead of reconstructing input samples, the decoder performs a task, e.g., classification, on the received signals. Applying different deep neural networks of encoder-decoder pairs on MNIST and CIFAR-10 image datasets, the classifier accuracy is shown to increase with the number of channel uses at the expense of longer service time. The peak age of task information (PAoTI) is introduced to analyze this accuracy-latency tradeoff when the age grows unless a received signal is classified correctly. By incorporating channel and traffic effects, design guidelines are obtained for task-oriented communications by characterizing how the PAoTI first decreases and then increases with the number of channel uses. A dynamic update mechanism is presented to adapt the number of channel uses to channel and traffic conditions, and reduce the PAoTI in task-oriented communications.

Cemil Vahapoglu, Timothy J. O'Shea, Tamoghna Roy et al.

The advancement of fifth generation (5G) wireless communication networks has created a greater demand for wireless resource management solutions that offer high data rates, extensive coverage, minimal latency and energy-efficient performance. Nonetheless, traditional approaches have shortcomings when it comes to computational complexity and their ability to adapt to dynamic conditions, creating a gap between theoretical analysis and the practical execution of algorithmic solutions for managing wireless resources. Deep learning-based techniques offer promising solutions for bridging this gap with their substantial representation capabilities. We propose a novel unsupervised deep learning framework, which is called NNBF, for the design of uplink receive multi-user single input multiple output (MU-SIMO) beamforming. The primary objective is to enhance the throughput by focusing on maximizing the sum-rate while also offering computationally efficient solution, in contrast to established conventional methods. We conduct experiments for several antenna configurations. Our experimental results demonstrate that NNBF exhibits superior performance compared to our baseline methods, namely, zero-forcing beamforming (ZFBF) and minimum mean square error (MMSE) equalizer. Additionally, NNBF is scalable to the number of single-antenna user equipments (UEs) while baseline methods have significant computational burden due to matrix pseudo-inverse operation.

Sajani Vithana, Sennur Ulukus

We investigate the problem of private read update write (PRUW) in federated submodel learning (FSL) with sparsification. In FSL, a machine learning model is divided into multiple submodels, where each user updates only the submodel that is relevant to the user's local data. PRUW is the process of privately performing FSL by reading from and writing to the required submodel without revealing the submodel index, or the values of updates to the databases. Sparsification is a widely used concept in learning, where the users update only a small fraction of parameters to reduce the communication cost. Revealing the coordinates of these selected (sparse) updates leaks privacy of the user. We show how PRUW in FSL can be performed with sparsification. We propose a novel scheme which privately reads from and writes to arbitrary parameters of any given submodel, without revealing the submodel index, values of updates, or the coordinates of the sparse updates, to databases. The proposed scheme achieves significantly lower reading and writing costs compared to what is achieved without sparsification.

Purbesh Mitra, Sennur Ulukus

We consider a gossip network, consisting of $n$ nodes, which tracks the information at a source. The source updates its information with a Poisson arrival process and also sends updates to the nodes in the network. The nodes themselves can exchange information among themselves to become as timely as possible. However, the network structure is sparse and irregular, i.e., not every node is connected to every other node in the network, rather, the order of connectivity is low, and varies across different nodes. This asymmetry of the network implies that the nodes in the network do not perform equally in terms of timelines. Due to the gossiping nature of the network, some nodes are able to track the source very timely, whereas, some nodes fall behind versions quite often. In this work, we investigate how the rate-constrained source should distribute its update rate across the network to maintain fairness regarding timeliness, i.e., the overall worst case performance of the network can be minimized. Due to the continuous search space for optimum rate allocation, we formulate this problem as a continuum-armed bandit problem and employ Gaussian process based Bayesian optimization to meet a trade-off between exploration and exploitation sequentially.

Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar et al.

Deep learning based joint source-channel coding (JSCC) has demonstrated significant advancements in data reconstruction compared to separate source-channel coding (SSCC). This superiority arises from the suboptimality of SSCC when dealing with finite block-length data. Moreover, SSCC falls short in reconstructing data in a multi-user and/or multi-resolution fashion, as it only tries to satisfy the worst channel and/or the highest quality data. To overcome these limitations, we propose a novel deep learning multi-resolution JSCC framework inspired by the concept of multi-task learning (MTL). This proposed framework excels at encoding data for different resolutions through hierarchical layers and effectively decodes it by leveraging both current and past layers of encoded data. Moreover, this framework holds great potential for semantic communication, where the objective extends beyond data reconstruction to preserving specific semantic attributes throughout the communication process. These semantic features could be crucial elements such as class labels, essential for classification tasks, or other key attributes that require preservation. Within this framework, each level of encoded data can be carefully designed to retain specific data semantics. As a result, the precision of a semantic classifier can be progressively enhanced across successive layers, emphasizing the preservation of targeted semantics throughout the encoding and decoding stages. We conduct experiments on MNIST and CIFAR10 dataset. The experiment with both datasets illustrates that our proposed method is capable of surpassing the SSCC method in reconstructing data with different resolutions, enabling the extraction of semantic features with heightened confidence in successive layers. This capability is particularly advantageous for prioritizing and preserving more crucial semantic features within the datasets.

Cemil Vahapoglu, Matin Mortaheb, Sennur Ulukus

Multi-task learning (MTL) is a learning paradigm to learn multiple related tasks simultaneously with a single shared network where each task has a distinct personalized header network for fine-tuning. MTL can be integrated into a federated learning (FL) setting if tasks are distributed across clients and clients have a single shared network, leading to personalized federated learning (PFL). To cope with statistical heterogeneity in the federated setting across clients which can significantly degrade the learning performance, we use a distributed dynamic weighting approach. To perform the communication between the remote parameter server (PS) and the clients efficiently over the noisy channel in a power and bandwidth-limited regime, we utilize over-the-air (OTA) aggregation and hierarchical federated learning (HFL). Thus, we propose hierarchical over-the-air (HOTA) PFL with a dynamic weighting strategy which we call HOTA-FedGradNorm. Our algorithm considers the channel conditions during the dynamic weight selection process. We conduct experiments on a wireless communication system dataset (RadComDynamic). The experimental results demonstrate that the training speed with HOTA-FedGradNorm is faster compared to the algorithms with a naive static equal weighting strategy. In addition, HOTA-FedGradNorm provides robustness against the negative channel effects by compensating for the channel conditions during the dynamic weight selection process.

Sahan Liyanaarachchi, Sennur Ulukus, Nail Akar

Query-based sampling has become an increasingly popular technique for monitoring Markov sources in pull-based update systems. However, most of the contemporary literature on this assumes an exponential distribution for query delay and often relies on the assumption that the feedback or replies to the queries are instantaneous. In this work, we relax both of these assumptions and find optimal sampling policies for monitoring continuous-time Markov chains (CTMC) under generic delay distributions. In particular, we show that one can obtain significant gains in terms of mean binary freshness (MBF) by employing a waiting based strategy for query-based sampling.

Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar et al.

Ensuring high-quality video content for wireless users has become increasingly vital. Nevertheless, maintaining a consistent level of video quality faces challenges due to the fluctuating encoded bitrate, primarily caused by dynamic video content, especially in live streaming scenarios. Video compression is typically employed to eliminate unnecessary redundancies within and between video frames, thereby reducing the required bandwidth for video transmission. The encoded bitrate and the quality of the compressed video depend on encoder parameters, specifically, the quantization parameter (QP). Poor choices of encoder parameters can result in reduced bandwidth efficiency and high likelihood of non-conformance. Non-conformance refers to the violation of the peak signal-to-noise ratio (PSNR) constraint for an encoded video segment. To address these issues, a real-time deep learning-based H.264 controller is proposed. This controller dynamically estimates the optimal encoder parameters based on the content of a video chunk with minimal delay. The objective is to maintain video quality in terms of PSNR above a specified threshold while minimizing the average bitrate of the compressed video. Experimental results, conducted on both QCIF dataset and a diverse range of random videos from public datasets, validate the effectiveness of this approach. Notably, it achieves improvements of up to 2.5 times in average bandwidth usage compared to the state-of-the-art adaptive bitrate video streaming, with a negligible non-conformance probability below $10^{-2}$.

Mustafa Doger, Sennur Ulukus

We consider the block withholding attacks on pools, more specifically the state-of-the-art Power Adjusting Withholding (PAW) attack. We propose a generalization called Temporary PAW (T-PAW) where the adversary withholds a fPoW from pool mining at most $T$-time even when no other block is mined. We show that PAW attack corresponds to $T\to\infty$ and is not optimal. In fact, the extra reward of T-PAW compared to PAW improves by an unbounded factor as adversarial hash fraction $α$, pool size $β$ and adversarial network influence $γ$ decreases. For example, the extra reward of T-PAW is 22 times that of PAW when an adversary targets a pool with $(α,β,γ)=(0.05,0.05,0)$. We show that honest mining is sub-optimal to T-PAW even when there is no difficulty adjustment and the adversarial revenue increase is non-trivial, e.g., for most $(α,β)$ at least $1\%$ within $2$ weeks in Bitcoin even when $γ=0$ (for PAW it was at most $0.01\%$). Hence, T-PAW exposes a significant structural weakness in pooled mining-its primary participants, small miners, are not only contributors but can easily turn into potential adversaries with immediate non-trivial benefits.

Mustafa Doger, Sennur Ulukus

Conventional double-spending attack models ignore the revenue losses stemming from the orphan blocks. On the other hand, selfish mining literature usually ignores the chance of the attacker to double-spend at no-cost in each attack cycle. In this paper, we give a rigorous stochastic analysis of an attack where the goal of the adversary is to double-spend while mining selfishly. To do so, we first combine stubborn and selfish mining attacks, \textit{i.e.}, construct a strategy where the attacker acts stubborn until its private branch reaches a certain length and then switches to act selfish. We provide the optimal stubbornness for each parameter regime. Next, we provide the maximum stubbornness that is still more profitable than honest mining and argue a connection between the level of stubbornness and the $k$-confirmation rule. We show that, at each attack cycle, if the level of stubbornness is higher than $k$, the adversary gets a free shot at double-spending. At each cycle, for a given stubbornness level, we rigorously formulate how great the probability of double-spending is. We further modify the attack in the stubborn regime in order to conceal the attack and increase the double-spending probability.

Matin Mortaheb, Sennur Ulukus

Decentralized and federated learning algorithms face data heterogeneity as one of the biggest challenges, especially when users want to learn a specific task. Even when personalized headers are used concatenated to a shared network (PF-MTL), aggregating all the networks with a decentralized algorithm can result in performance degradation as a result of heterogeneity in the data. Our algorithm uses exchanged gradients to calculate the correlations among tasks automatically, and dynamically adjusts the communication graph to connect mutually beneficial tasks and isolate those that may negatively impact each other. This algorithm improves the learning performance and leads to faster convergence compared to the case where all clients are connected to each other regardless of their correlations. We conduct experiments on a synthetic Gaussian dataset and a large-scale celebrity attributes (CelebA) dataset. The experiment with the synthetic data illustrates that our proposed method is capable of detecting tasks that are positively and negatively correlated. Moreover, the results of the experiments with CelebA demonstrate that the proposed method may produce significantly faster training results than fully-connected networks.

Mustafa Doger, Sennur Ulukus

Bitcoin's (BTC) Difficulty Adjustment Algorithm (DAA) has been a source of vulnerability for incentive attacks such as selfish mining, block withholding and coin hopping strategies. In this paper, first, we rigorously study the short-term revenue change per hashpower of the adversarial and honest miners for these incentive attacks. To study the long-term effects, we introduce a new efficiency metric defined as the revenue/cost per hashpower per time for the attacker and the honest miners. Our results indicate that the short-term benefits of intermittent mining strategies are negligible compared to the original selfish mining attack, and in the long-term, selfish mining provides better efficiency. We further demonstrate that a coin hopping strategy between BTC and Bitcoin Cash (BCH) relying on BTC DAA benefits the loyal honest miners of BTC in the same way and to the same extent per unit of computational power as it does the hopper in the short-term. For the long-term, we establish a new boundary between the selfish mining and coin hopping attack, identifying the optimal efficient strategy for each parameter. For block withholding strategies, it turns out, the honest miners outside the pool profit from the attack, usually even more than the attacker both in the short-term and the long-term. Moreover, a Power Adjusting Withholding (PAW) attacker does not necessarily observe a profit lag in the short-term. In other words, even without a difficulty adjustment, a PAW attacker makes profits. It has been long thought that the profit lag of selfish mining is among the main reasons why such an attack has not been observed in practice. We show that such a barrier does not apply to PAW and relatively small pools are at an immediate threat.

Melih Bastopcu, Sennur Ulukus

We consider a system where a human operator processes a sequence of tasks that are similar in nature under a total time constraint. In these systems, the performance of the operator depends on its past utilization. This is akin to $\textit{state-dependent}$ channels where the past actions of the transmitter affects the future quality of the channel (also known as $\textit{action-dependent}$ or $\textit{use-dependent}$ channels). For $\textit{human channels}$, a well-known psychological phenomena, known as $\textit{Yerkes-Dodson law}$, states that a human operator performs worse when he/she is over-utilized or under-utilized. Over such a $\textit{use-dependent}$ human channel, we consider the problem of maximizing a utility function, which is monotonically increasing and concave in the time allocated for each task, under explicit minimum and maximum $\textit{utilization}$ constraints. We show that the optimal solution is to keep the utilization ratio of the operator as high as possible, and to process all the tasks. We prove that the optimal policy consists of two major strategies: utilize the operator without resting until reaching the maximum allowable utilization ratio, and then alternate between working and resting the operator each time reaching the maximum allowable utilization at the end of work-period. We show that even though the tasks are similar in difficulty, the time allocated for the tasks can be different depending on the strategy in which a task is processed; however, the tasks processed in the same strategy are processed equally.

Subhankar Banerjee, Stavros Mitrolaris, Sennur Ulukus

We consider a quantum switch with a finite number of quantum memory registers that aims to serve multipartite entanglement requests among $N$ users. We propose scheduling policies that aim to optimize the average number of requests served per unit time by efficiently utilizing the switch's available memory. To measure the performance of the scheduling policies, we employ the newly introduced metric of age of entanglement establishment (AoEE). We formulate the scheduling problem in a restless multi-armed bandit (RMAB) framework. We show that the scheduling of entanglement requests is indexable. Subsequently, we find a closed-form expression of the Whittle index for all possible request-age pairs. By modeling the Whittle index of each request as its reward and its cardinality as its cost, we formulate the memory-constrained scheduling problem as a $0$-$1$ knapsack problem and solve it via dynamic programming. Furthermore, we consider two low-complexity sequential greedy policies that leverage two different modified Whittle indices.

Weihang Cao, Mustafa Doger, Sennur Ulukus

The security and decentralization of Proof-of-Work (PoW) have been well-tested in existing blockchain systems. However, its tremendous energy waste has raised concerns about sustainability. Proof-of-Useful-Work (PoUW) aims to redirect the meaningless computation to meaningful tasks such as solving machine learning (ML) problems, giving rise to the branch of Proof-of-Learning (PoL). While previous studies have proposed various PoLs, they all, to some degree, suffer from security, decentralization, or efficiency issues. In this paper, we propose a PoL framework that trains ML models efficiently while maintaining blockchain security in a fully distributed manner. We name the framework SEDULity, which stands for a Secure, Efficient, Distributed, and Useful Learning-based blockchain system. Specifically, we encode the template block into the training process and design a useful function that is difficult to solve but relatively easy to verify, as a substitute for the PoW puzzle. We show that our framework is distributed, secure, and efficiently trains ML models. We further demonstrate that the proposed PoL framework can be extended to other types of useful work and design an incentive mechanism to incentivize task verification. We show theoretically that a rational miner is incentivized to train fully honestly with well-designed system parameters. Finally, we present simulation results to demonstrate the performance of our framework and validate our analysis.

Matin Mortaheb, Erciyes Karakaya, Sennur Ulukus

Semantic communication aims to transmit information most relevant to a task rather than raw data, offering significant gains in communication efficiency for applications such as telepresence, augmented reality, and remote sensing. Recent transformer-based approaches have used self-attention maps to identify informative regions within images, but they often struggle in complex scenes with multiple objects, where self-attention lacks explicit task guidance. To address this, we propose a novel Multi-Modal Semantic Communication framework that integrates text-based user queries to guide the information extraction process. Our proposed system employs a cross-modal attention mechanism that fuses visual features with language embeddings to produce soft relevance scores over the visual data. Based on these scores and the instantaneous channel bandwidth, we use an algorithm to transmit image patches at adaptive resolutions using independently trained encoder-decoder pairs, with total bitrate matching the channel capacity. At the receiver, the patches are reconstructed and combined to preserve task-critical information. This flexible and goal-driven design enables efficient semantic communication in complex and bandwidth-constrained environments.

Cemil Vahapoglu, Timothy J. O'Shea, Wan Liu et al.

Beamforming has significance for enhancing spectral efficiency and mitigating interference in multi-antenna wireless systems, facilitating spatial multiplexing and diversity in dense and high mobility scenarios. Traditional beamforming techniques such as zero-forcing beamforming (ZFBF) and minimum mean square error (MMSE) beamforming experience performance deterioration under adverse channel conditions. Deep learning-based beamforming offers an alternative with nonlinear mappings from channel state information (CSI) to beamforming weights by improving robustness against dynamic channel environments. Transformer-based models are particularly effective due to their ability to model long-range dependencies across time and frequency. However, their quadratic attention complexity limits scalability in large OFDM grids. Recent studies address this issue through sparse attention mechanisms that reduce complexity while maintaining expressiveness, yet often employ patterns that disregard channel dynamics, as they are not specifically designed for wireless communication scenarios. In this work, we propose a Doppler-aware Sparse Neural Network Beamforming (Doppler-aware Sparse NNBF) model that incorporates a channel-adaptive sparse attention mechanism in a multi-user single-input multiple-output (MU-SIMO) setting. The proposed sparsity structure is configurable along 2D time-frequency axes based on channel dynamics and is theoretically proven to ensure full connectivity within p hops, where p is the number of attention heads. Simulation results under urban macro (UMa) channel conditions show that Doppler-aware Sparse NNBF significantly outperforms both a fixed-pattern baseline, referred to as Standard Sparse NNBF, and conventional beamforming techniques ZFBF and MMSE beamforming in high mobility scenarios, while maintaining structured sparsity with a controlled number of attended keys per query.

Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar et al.

Providing wireless users with high-quality video content has become increasingly important. However, ensuring consistent video quality poses challenges due to variable encoded bitrate caused by dynamic video content and fluctuating channel bitrate caused by wireless fading effects. Suboptimal selection of encoder parameters can lead to video quality loss due to underutilized bandwidth or the introduction of video artifacts due to packet loss. To address this, a real-time deep learning based H.264 controller is proposed. This controller leverages instantaneous channel quality data driven from the physical layer, along with the video chunk, to dynamically estimate the optimal encoder parameters with a negligible delay in real-time. The objective is to maintain an encoded video bitrate slightly below the available channel bitrate. Experimental results, conducted on both QCIF dataset and a diverse selection of random videos from public datasets, validate the effectiveness of the approach. Remarkably, improvements of 10-20 dB in PSNR with repect to the state-of-the-art adaptive bitrate video streaming is achieved, with an average packet drop rate as low as 0.002.

Yalin E. Sagduyu, Tugba Erpek, Aylin Yener et al.

Semantic communications conveys task-relevant meaning rather than focusing solely on message reconstruction, improving bandwidth efficiency and robustness for next-generation wireless systems. However, learned semantic representations can still leak sensitive information to unintended receivers (eavesdroppers). This paper presents a deep learning-based semantic communication framework that jointly supports multiple receiver tasks while explicitly limiting semantic leakage to an eavesdropper. The legitimate link employs a learned encoder at the transmitter, while the receiver trains decoders for semantic inference and data reconstruction. The security problem is formulated via an iterative min-max optimization in which an eavesdropper is trained to improve its semantic inference, while the legitimate transmitter-receiver pair is trained to preserve task performance while reducing the eavesdropper's success. We also introduce an auxiliary layer that superimposes a cooperative, adversarially crafted perturbation on the transmitted waveform to degrade semantic leakage to an eavesdropper. Performance is evaluated over Rayleigh fading channels with additive white Gaussian noise using MNIST and CIFAR-10 datasets. Semantic accuracy and reconstruction quality improve with increasing latent dimension, while the min-max mechanism reduces the eavesdropper's inference performance significantly without degrading the legitimate receiver. The perturbation layer is successful in reducing semantic leakage even when the legitimate link is trained only for its own task. This comprehensive framework motivates semantic communication designs with tunable, end-to-end privacy against adaptive adversaries in realistic wireless settings.

Ismail Cosandal, Sennur Ulukus

The groundbreaking metric age of information (AoI) has been introduced to measure information freshness in communication networks. As transformational as it is, AoI metric falls short in some applications, such as remote monitoring, since it is a semantic-agnostic metric which does not consider the dynamics of the random process. There is a need to quantify the performance of a remote estimator via a metric that combines freshness and semantic aspects. To this end, in this paper, we introduce a novel metric coined age of staleness (AoS) that measures when the last time that the current estimation was correct. First, we analyze a simple scenario where an $n$-ary symmetric Markov source is observed by a monitor via a constant sampling rate, obtain a closed-form expression for the AoS, and show that it is a monotonically decreasing function of the sampling rate. Next, we consider multiple distinct Markov sources, and formulate an optimization problem, where the remote monitor allocates the total sampling rate to tracking the sources. Although the optimization problem is non-convex, its structure is suitable for obtaining a near-optimal solution using the polyblock algorithm, which leverages the monotonicity of the objective function. While the new AoS metric could be applicable in many scenarios, we believe it is particularly well-suited for a digital twin network (DTN) where multiple physical objects (POs) are monitored with a total sampling rate constraint to maintain a digital representation of them, namely, their digital twin (DT).

Sahan Liyanaarachchi, Sennur Ulukus, Nail Akar

The study of optimal preemption policies for status update systems has been a recurring topic in the age of information (AoI) literature, where threshold-based structures have been shown to be optimal under a generate-at-will update generation model under certain assumptions. In this work, we study the effectiveness of threshold-based policies for a system with random update arrivals. In this regard, we introduce an analytical framework for evaluating the AoI of multi-threshold preemption policies and present interesting characteristics of the structure of the optimal preemption policy. We show the effectiveness of these threshold-based policies over the traditional probabilistic preemption policies and single-threshold policies, where we observe that significant gains in terms of AoI can be obtained by utilizing both the age of the packet and the age of the system when designing these preemption policies.

Purbesh Mitra, Priyanka Kaswan, Sennur Ulukus

Mixture-of-Agents (MoA) has recently been proposed as a method to enhance performance of large language models (LLMs), enabling multiple individual LLMs to work together for collaborative inference. This collaborative approach results in improved responses to user prompts compared to relying on a single LLM. In this paper, we consider such an MoA architecture in a distributed setting, where LLMs operate on individual edge devices, each uniquely associated with a user and equipped with its own distributed computing power. These devices exchange information using decentralized gossip algorithms, allowing different device nodes to talk without the supervision of a centralized server. In the considered setup, different users have their own LLM models to address user prompts. Additionally, the devices gossip either their own user-specific prompts or augmented prompts to generate more refined answers to certain queries. User prompts are temporarily stored in the device queues when their corresponding LLMs are busy. Given the memory limitations of edge devices, it is crucial to ensure that the average queue sizes in the system remain bounded. In this paper, we address this by theoretically calculating the queuing stability conditions for the device queues under reasonable assumptions, which we validate experimentally as well. Further, we demonstrate through experiments, leveraging open-source LLMs for the implementation of distributed MoA, that certain MoA configurations produce higher-quality responses compared to others, as evaluated on AlpacaEval 2.0 benchmark. The implementation is available at: https://github.com/purbeshmitra/distributed_moa.

Lei Hu, Mohamed Nomeir, Alptug Aytekin et al.

We study exact-regenerating codes for entanglement-assisted distributed storage systems. Consider an $(n,k,d,α,β_{\mathsf{q}},B)$ distributed system that stores a file of $B$ classical symbols across $n$ nodes with each node storing $α$ symbols. A data collector can recover the file by accessing any $k$ nodes. When a node fails, any $d$ surviving nodes share an entangled state, and each of them transmits a quantum system of $β_{\mathsf{q}}$ qudits to a newcomer. The newcomer then performs a measurement on the received quantum systems to generate its storage. Recent work [1] showed that, under functional repair where the regenerated content may differ from that of the failed node, there exists a unique optimal regenerating point that \emph{simultaneously minimizes both storage $α$ and repair bandwidth $d β_{\mathsf{q}}$} when $d \geq 2k-2$. In this paper, we show that, under \emph{exact repair}, where the newcomer reproduces exactly the same content as the failed node, this optimal point remains achievable. Our construction builds on the classical product-matrix framework and the Calderbank-Shor-Steane (CSS)-based stabilizer formalism.

Shreya Meel, Mohamed Nomeir, Sennur Ulukus

We rethink the definition of privacy in multi-server, graph-replicated private information retrieval (PIR) systems, and introduce a novel setting where the user's privacy is governed by the servers' storage structure. In particular, while retrieving a message from a server, the user is concerned with hiding their desired message index from the server, only if the server stores the corresponding message. We coin this privacy requirement as local user privacy and the resulting PIR problem as local PIR on the graph. Our goal is to measure the gain in communication efficiency of local PIR, compared to that of canonical PIR, by establishing its capacity, i.e., the maximum number of message symbols retrieved, per downloaded symbol. To this end, we observe a remarkable gain in the local PIR capacity of graphs, that are disjoint union of distinct graphs, which is multiplicative, compared to the PIR capacity, when the individual graphs are identical. For connected graphs, we propose schemes to establish capacity lower bounds for edge-transitive and bipartite graphs, which are greater than the best-known PIR capacity bounds. Finally, we derive the exact local PIR capacity for the cyclic graph, and the path graph with an odd number of vertices.

Purbesh Mitra, Sennur Ulukus

Recent advancements in the reasoning capabilities of large language models (LLMs) show that employing group relative policy optimization (GRPO) algorithm for reinforcement learning (RL) training allows the models to use more thinking/reasoning tokens for generating better responses. However, LLMs can generate only a finite amount of tokens while maintaining attention to the previously generated tokens. This limit, also known as the context size of an LLM, is a bottleneck in LLM reasoning with arbitrarily large number of tokens. To think beyond the limit of context size, an LLM must employ a modular thinking strategy to reason over multiple rounds. In this work, we propose $\textbf{MOTIF: Modular Thinking via Reinforcement Finetuning}$ -- an RL training method for generating thinking tokens in multiple rounds, effectively allowing the model to think with additional context size. We trained the open-source model Qwen2.5-3B-Instruct on GSM8K dataset via parameter efficient fine-tuning and tested its accuracy on MATH500 and AIME2024 benchmarks. Our experiments show 3.8\% and 3.3\% improvements over vanilla GRPO based training in the respective benchmarks. Furthermore, this improvement was achieved with only 15\% of samples, thus demonstrating sample efficiency of MOTIF. Our code and models are available at https://github.com/purbeshmitra/MOTIF and https://huggingface.co/purbeshmitra/MOTIF, respectively.

Mohamed Nomeir, Shreya Meel, Sennur Ulukus

We reformulate the definition of privacy in the private information retrieval (PIR) problem to accommodate flexible privacy requirements. We focus on graph-replicated PIR, with a generalized privacy requirement, instead of requiring all messages to be private from all servers, during retrieval. Towards this, we define a privacy requirement set for each server, which can be an arbitrary subset of all message indices, as long as the stored message indices are in their privacy requirement set. Since both the storage and privacy requirement sets have many possibilities, we focus on two specific storage settings, namely the path and cyclic graphs. We consider several privacy settings for each of them, which are not necessarily the same, to give different examples for privacy sets. Of particular interest are the privacy sets that comprise the indices of messages stored at servers within a neighborhood range. The neighborhood range parameter allows a transition from the recently introduced local PIR [1] to the standard graph-replicated PIR. In these cases, we derive bounds on the capacity or find the exact capacity.

Arunabh Srivastava, Sennur Ulukus

We consider a network consisting of $n$ nodes connected in a ring formation and a source that generates updates according to a renewal process and disseminates them to the ring network according to a Poisson process. The nodes in the network gossip with each other according to a push-based gossiping protocol, and disseminate version updates. Gossip between two neighbors happens at the arrivals of renewal processes with finite mean and variance. All renewal processes and Poisson processes in the network are independent but not identically distributed. We consider both uni-directional ring networks and bi-directional ring networks. We use version age of information to quantify the freshness of information at each node. Prior work has used the stochastic hybrid systems (SHS) approach or a first passage percolation (FPP) approach to analyze ring networks with edges following identical Poisson processes. In this work, we use a sample-path backtracking approach to characterize the probabilistic scaling of the version age of information of an arbitrary node in the gossip network, where each edge follows an independent but not identically distributed renewal process. We show that the version age of information of any node in the network is stochastically equivalent to $\sqrt{n}$ at any time instant after the node has received its first update from the source.

Arunabh Srivastava, Mohammad A., Khojastepour et al.

Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multi-agent plan execution platform that interprets natural-language plans while enforcing stepwise execution through constraints and rubrics. RunAgent bridges the expressiveness of natural language with the determinism of programming via an agentic language with explicit control constructs (e.g., \texttt{IF}, \texttt{GOTO}, \texttt{FORALL}). Beyond verifying syntactic and semantic verification of the step output, which is performed based on the specific instruction of each step, RunAgent autonomously derives and validates constraints based on the description of the task and its instance at each step. RunAgent also dynamically selects among LLM-based reasoning, tool usage, and code generation and execution (e.g., in Python), and incorporates error correction mechanisms to ensure correctness. Finally, RunAgent filters the context history by retaining only relevant information during the execution of each step. Evaluations on Natural-plan and SciBench Datasets demonstrate that RunAgent outperforms baseline LLMs and state-of-the-art PlanGEN methods.

Yalin E. Sagduyu, Tugba Erpek, Aylin Yener et al.

This paper explores opportunities and challenges of task (goal)-oriented and semantic communications for next-generation (NextG) communication networks through the integration of multi-task learning. This approach employs deep neural networks representing a dedicated encoder at the transmitter and multiple task-specific decoders at the receiver, collectively trained to handle diverse tasks including semantic information preservation, source input reconstruction, and integrated sensing and communications. To extend the applicability from point-to-point links to multi-receiver settings, we envision the deployment of decoders at various receivers, where decentralized learning addresses the challenges of communication load and privacy concerns, leveraging federated learning techniques that distribute model updates across decentralized nodes. However, the efficacy of this approach is contingent on the robustness of the employed deep learning models. We scrutinize potential vulnerabilities stemming from adversarial attacks during both training and testing phases. These attacks aim to manipulate both the inputs at the encoder at the transmitter and the signals received over the air on the receiver side, highlighting the importance of fortifying semantic communications against potential multi-domain exploits. Overall, the joint and robust design of task-oriented communications, semantic communications, and integrated sensing and communications in a multi-task learning framework emerges as the key enabler for context-aware, resource-efficient, and secure communications ultimately needed in NextG network systems.

Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar et al.

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face unique challenges: (i) the retrieval process may select irrelevant entries to user query (e.g., images, documents), and (ii) vision-language models or multi-modal language models like GPT-4o may hallucinate when processing these entries to generate RAG output. In this paper, we aim to address the first challenge, i.e, improving the selection of relevant context from the knowledge-base in retrieval phase of the multi-modal RAG. Specifically, we leverage the relevancy score (RS) measure designed in our previous work for evaluating the RAG performance to select more relevant entries in retrieval process. The retrieval based on embeddings, say CLIP-based embedding, and cosine similarity usually perform poorly particularly for multi-modal data. We show that by using a more advanced relevancy measure, one can enhance the retrieval process by selecting more relevant pieces from the knowledge-base and eliminate the irrelevant pieces from the context by adaptively selecting up-to-$k$ entries instead of fixed number of entries. Our evaluation using COCO dataset demonstrates significant enhancement in selecting relevant context and accuracy of the generated response.

Ismail Cosandal, Sennur Ulukus, Nail Akar

Age of incorrect information (AoII) is a recently proposed freshness and mismatch metric that penalizes an incorrect estimation along with its duration. Therefore, keeping track of AoII requires the knowledge of both the source and estimation processes. In this paper, we consider a time-slotted pull-based remote estimation system under a sampling rate constraint where the information source is a general discrete-time Markov chain (DTMC) process. Moreover, packet transmission times from the source to the monitor are non-zero which disallows the monitor to have perfect information on the actual AoII process at any time. Hence, for this pull-based system, we propose the monitor to maintain a sufficient statistic called {\em belief} which stands for the joint distribution of the age and source processes to be obtained from the history of all observations. Using belief, we first propose a maximum a posteriori (MAP) estimator to be used at the monitor as opposed to existing martingale estimators in the literature. Second, we obtain the optimality equations from the belief-MDP (Markov decision process) formulation. Finally, we propose two belief-dependent policies one of which is based on deep reinforcement learning, and the other one is a threshold-based policy based on the instantaneous expected AoII.

Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar et al.

Retrieval-augmented generation (RAG) improves large language models (LLMs) by using external knowledge to guide response generation, reducing hallucinations. However, RAG, particularly multi-modal RAG, can introduce new hallucination sources: (i) the retrieval process may select irrelevant pieces (e.g., documents, images) as raw context from the database, and (ii) retrieved images are processed into text-based context via vision-language models (VLMs) or directly used by multi-modal language models (MLLMs) like GPT-4o, which may hallucinate. To address this, we propose a novel framework to evaluate the reliability of multi-modal RAG using two performance measures: (i) the relevancy score (RS), assessing the relevance of retrieved entries to the query, and (ii) the correctness score (CS), evaluating the accuracy of the generated response. We train RS and CS models using a ChatGPT-derived database and human evaluator samples. Results show that both models achieve ~88% accuracy on test data. Additionally, we construct a 5000-sample human-annotated database evaluating the relevancy of retrieved pieces and the correctness of response statements. Our RS model aligns with human preferences 20% more often than CLIP in retrieval, and our CS model matches human preferences ~91% of the time. Finally, we assess various RAG systems' selection and generation performances using RS and CS.

Matin Mortaheb, Erciyes Karakaya, Mohammad A. Amir Khojastepour et al.

The transformer structure employed in large language models (LLMs), as a specialized category of deep neural networks (DNNs) featuring attention mechanisms, stands out for their ability to identify and highlight the most relevant aspects of input data. Such a capability is particularly beneficial in addressing a variety of communication challenges, notably in the realm of semantic communication where proper encoding of the relevant data is critical especially in systems with limited bandwidth. In this work, we employ vision transformers specifically for the purpose of compression and compact representation of the input image, with the goal of preserving semantic information throughout the transmission process. Through the use of the attention mechanism inherent in transformers, we create an attention mask. This mask effectively prioritizes critical segments of images for transmission, ensuring that the reconstruction phase focuses on key objects highlighted by the mask. Our methodology significantly improves the quality of semantic communication and optimizes bandwidth usage by encoding different parts of the data in accordance with their semantic information content, thus enhancing overall efficiency. We evaluate the effectiveness of our proposed framework using the TinyImageNet dataset, focusing on both reconstruction quality and accuracy. Our evaluation results demonstrate that our framework successfully preserves semantic information, even when only a fraction of the encoded data is transmitted, according to the intended compression rates.

Yalin E. Sagduyu, Tugba Erpek, Aylin Yener et al.

This paper introduces a deep learning approach to dynamic spectrum access, leveraging the synergy of multi-modal image and spectrum data for the identification of potential transmitters. We consider an edge device equipped with a camera that is taking images of potential objects such as vehicles that may harbor transmitters. Recognizing the computational constraints and trust issues associated with on-device computation, we propose a collaborative system wherein the edge device communicates selectively processed information to a trusted receiver acting as a fusion center, where a decision is made to identify whether a potential transmitter is present, or not. To achieve this, we employ task-oriented communications, utilizing an encoder at the transmitter for joint source coding, channel coding, and modulation. This architecture efficiently transmits essential information of reduced dimension for object classification. Simultaneously, the transmitted signals may reflect off objects and return to the transmitter, allowing for the collection of target sensing data. Then the collected sensing data undergoes a second round of encoding at the transmitter, with the reduced-dimensional information communicated back to the fusion center through task-oriented communications. On the receiver side, a decoder performs the task of identifying a transmitter by fusing data received through joint sensing and task-oriented communications. The two encoders at the transmitter and the decoder at the receiver are jointly trained, enabling a seamless integration of image classification and wireless signal detection. Using AWGN and Rayleigh channel models, we demonstrate the effectiveness of the proposed approach, showcasing high accuracy in transmitter identification across diverse channel conditions while sustaining low latency in decision making.

Yalin E. Sagduyu, Tugba Erpek, Aylin Yener et al.

In this paper, we address task-oriented (or goal-oriented) communications where an encoder at the transmitter learns compressed latent representations of data, which are then transmitted over a wireless channel. At the receiver, a decoder performs a machine learning task, specifically for classifying the received signals. The deep neural networks corresponding to the encoder-decoder pair are jointly trained, taking both channel and data characteristics into account. Our objective is to achieve high accuracy in completing the underlying task while minimizing the number of channel uses determined by the encoder's output size. To this end, we propose a multi-round, multi-task learning (MRMTL) approach for the dynamic update of channel uses in multi-round transmissions. The transmitter incrementally sends an increasing number of encoded samples over the channel based on the feedback from the receiver, and the receiver utilizes the signals from a previous round to enhance the task performance, rather than only considering the latest transmission. This approach employs multi-task learning to jointly optimize accuracy across varying number of channel uses, treating each configuration as a distinct task. By evaluating the confidence of the receiver in task decisions, MRMTL decides on whether to allocate additional channel uses in multiple rounds. We characterize both the accuracy and the delay (total number of channel uses) of MRMTL, demonstrating that it achieves the accuracy close to that of conventional methods requiring large numbers of channel uses, but with reduced delay by incorporating signals from a prior round. We consider the CIFAR-10 dataset, convolutional neural network architectures, and AWGN and Rayleigh channel models for performance evaluation. We show that MRMTL significantly improves the efficiency of task-oriented communications, balancing accuracy and latency effectively.

Cemil Vahapoglu, Timothy J. O'Shea, Wan Liu et al.

The literature is abundant with methodologies focusing on using transformer architectures due to their prominence in wireless signal processing and their capability to capture long-range dependencies via attention mechanisms. In particular, depthwise separable convolutions enhance parameter efficiency for the process of high-dimensional data characteristics of MIMO systems. In this work, we introduce a novel unsupervised deep learning framework that integrates depthwise separable convolutions and transformers to generate beamforming weights under imperfect channel state information (CSI) for a multi-user single-input multiple-output (MU-SIMO) system in dense urban environments. The primary goal is to enhance throughput by maximizing sum-rate while ensuring reliable communication. Spectral efficiency and block error rate (BLER) are considered as performance metrics. Experiments are carried out under various conditions to compare the performance of the proposed NNBF framework against baseline methods zero-forcing beamforming (ZFBF) and minimum mean square error (MMSE) beamforming. Experimental results demonstrate the superiority of the proposed framework over the baseline techniques.

Matin Mortaheb, Mohammad A. Amir Khojastepour, Sennur Ulukus

Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication systems. In this work, we introduce a channel-aware adaptive framework for semantic communication, where different regions of the image are encoded and compressed based on their semantic content. By employing vision transformers, we interpret the attention mask as a measure of the semantic contents of the patches and dynamically categorize the patches to be compressed at various rates as a function of the instantaneous channel bandwidth. Our method enhances communication efficiency by adapting the encoding resolution to the content's relevance, ensuring that even in highly constrained environments, critical information is preserved. We evaluate the proposed adaptive transmission framework using the TinyImageNet dataset, measuring both reconstruction quality and accuracy. The results demonstrate that our approach maintains high semantic fidelity while optimizing bandwidth, providing an effective solution for transmitting multi-resolution data in limited bandwidth conditions.

Shreya Meel, Mohamed Nomeir, Pasan Dissanayake et al.

Transparency and explainability are two important aspects to be considered when employing black-box machine learning models in high-stake applications. Providing counterfactual explanations is one way of catering this requirement. However, this also poses a threat to the privacy of the institution that is providing the explanation, as well as the user who is requesting it. In this work, we are primarily concerned with the user's privacy who wants to retrieve a counterfactual instance, without revealing their feature vector to the institution. Our framework retrieves the exact nearest neighbor counterfactual explanation from a database of accepted points while achieving perfect, information-theoretic, privacy for the user. First, we introduce the problem of private counterfactual retrieval (PCR) and propose a baseline PCR scheme that keeps the user's feature vector information-theoretically private from the institution. Building on this, we propose two other schemes that reduce the amount of information leaked about the institution database to the user, compared to the baseline scheme. Second, we relax the assumption of mutability of all features, and consider the setting of immutable PCR (I-PCR). Here, the user retrieves the nearest counterfactual without altering a private subset of their features, which constitutes the immutable set, while keeping their feature vector and immutable set private from the institution. For this, we propose two schemes that preserve the user's privacy information-theoretically, but ensure varying degrees of database privacy. Third, we extend our PCR and I-PCR schemes to incorporate user's preference on transforming their attributes, so that a more actionable explanation can be received. Finally, we present numerical results to support our theoretical findings, and compare the database leakage of the proposed schemes.

Sahan Liyanaarachchi, Kanchana Thilakarathna, Sennur Ulukus

In many federated learning (FL) models, a common strategy employed to ensure the progress in the training process, is to wait for at least $M$ clients out of the total $N$ clients to send back their local gradients based on a reporting deadline $T$, once the parameter server (PS) has broadcasted the global model. If enough clients do not report back within the deadline, the particular round is considered to be a failed round and the training round is restarted from scratch. If enough clients have responded back, the round is deemed successful and the local gradients of all the clients that responded back are used to update the global model. In either case, the clients that failed to report back an update within the deadline would have wasted their computational resources. Having a tighter deadline (small $T$) and waiting for a larger number of participating clients (large $M$) leads to a large number of failed rounds and therefore greater communication cost and computation resource wastage. However, having a larger $T$ leads to longer round durations whereas smaller $M$ may lead to noisy gradients. Therefore, there is a need to optimize the parameters $M$ and $T$ such that communication cost and the resource wastage is minimized while having an acceptable convergence rate. In this regard, we show that the average age of a client at the PS appears explicitly in the theoretical convergence bound, and therefore, can be used as a metric to quantify the convergence of the global model. We provide an analytical scheme to select the parameters $M$ and $T$ in this setting.

Purbesh Mitra, Sennur Ulukus

We consider an asynchronous decentralized learning system, which consists of a network of connected devices trying to learn a machine learning model without any centralized parameter server. The users in the network have their own local training data, which is used for learning across all the nodes in the network. The learning method consists of two processes, evolving simultaneously without any necessary synchronization. The first process is the model update, where the users update their local model via a fixed number of stochastic gradient descent steps. The second process is model mixing, where the users communicate with each other via randomized gossiping to exchange their models and average them to reach consensus. In this work, we investigate the staleness criteria for such a system, which is a sufficient condition for convergence of individual user models. We show that for network scaling, i.e., when the number of user devices $n$ is very large, if the gossip capacity of individual users scales as $Ω(\log n)$, we can guarantee the convergence of user models in finite time. Furthermore, we show that the bounded staleness can only be guaranteed by any distributed opportunistic scheme by $Ω(n)$ scaling.

Matin Mortaheb, Priyanka Kaswan, Sennur Ulukus

Federated learning (FL) is a collaborative approach where multiple clients, coordinated by a parameter server (PS), train a unified machine-learning model. The approach, however, suffers from two key challenges: data heterogeneity and communication overhead. Data heterogeneity refers to inconsistencies in model training arising from heterogeneous data at different clients. Communication overhead arises from the large volumes of parameter updates exchanged between the PS and clients. Existing solutions typically address these challenges separately. This paper introduces a new communication-efficient algorithm that uses the age of information metric to simultaneously tackle both limitations of FL. We introduce age vectors at the PS, which keep track of how often the different model parameters are updated from the clients. The PS uses this to selectively request updates for specific gradient indices from each client. Further, the PS employs age vectors to identify clients with statistically similar data and group them into clusters. The PS combines the age vectors of the clustered clients to efficiently coordinate gradient index updates among clients within a cluster. We evaluate our approach using the MNIST and CIFAR10 datasets in highly non-i.i.d. settings. The experimental results show that our proposed method can expedite training, surpassing other communication-efficient strategies in efficiency.

Mohamed Nomeir, Pasan Dissanayake, Shreya Meel et al.

Transparency and explainability are two extremely important aspects to be considered when employing black-box machine learning models in high-stake applications. Providing counterfactual explanations is one way of fulfilling this requirement. However, this also poses a threat to the privacy of both the institution that is providing the explanation as well as the user who is requesting it. In this work, we propose multiple schemes inspired by private information retrieval (PIR) techniques which ensure the \emph{user's privacy} when retrieving counterfactual explanations. We present a scheme which retrieves the \emph{exact} nearest neighbor counterfactual explanation from a database of accepted points while achieving perfect (information-theoretic) privacy for the user. While the scheme achieves perfect privacy for the user, some leakage on the database is inevitable which we quantify using a mutual information based metric. Furthermore, we propose strategies to reduce this leakage to achieve an advanced degree of database privacy. We extend these schemes to incorporate user's preference on transforming their attributes, so that a more actionable explanation can be received. Since our schemes rely on finite field arithmetic, we empirically validate our schemes on real datasets to understand the trade-off between the accuracy and the finite field sizes. Finally, we present numerical results to support our theoretical findings, and compare the database leakage of the proposed schemes.