Marios Kountouris

Federico Boccardi, Hossein Shokri-Ghadikolaei, Gabor Fodor et al.

Motivated by the intrinsic characteristics of mmWave technologies, we discuss the possibility of an authorization regime that allows spectrum sharing between multiple operators, also referred to as spectrum pooling. In particular, considering user rate as the performance measure, we assess the benefit of coordination among the networks of different operators, study the impact of beamforming both at the base stations and at the user terminals, and analyze the pooling performance at different frequency carriers. We also discuss the enabling spectrum mechanisms, architectures, and protocols required to make spectrum pooling work in real networks. Our initial results show that, from a technical perspective, spectrum pooling at mmWave has the potential for a more efficient spectrum use than a traditional exclusive spectrum allocation to a single operator. However, further studies are needed in order to reach a thorough understanding of this matter, and we hope that this paper will help stimulate further research in this area.

Matteo Zecchin, Sangwoo Park, Osvaldo Simeone et al.

This work takes a critical look at the application of conventional machine learning methods to wireless communication problems through the lens of reliability and robustness. Deep learning techniques adopt a frequentist framework, and are known to provide poorly calibrated decisions that do not reproduce the true uncertainty caused by limitations in the size of the training data. Bayesian learning, while in principle capable of addressing this shortcoming, is in practice impaired by model misspecification and by the presence of outliers. Both problems are pervasive in wireless communication settings, in which the capacity of machine learning models is subject to resource constraints and training data is affected by noise and interference. In this context, we explore the application of the framework of robust Bayesian learning. After a tutorial-style introduction to robust Bayesian learning, we showcase the merits of robust Bayesian learning on several important wireless communication problems in terms of accuracy, calibration, and robustness to outliers and misspecification.

Eunjeong Jeong, Marios Kountouris

Personalization in federated learning (FL) functions as a coordinator for clients with high variance in data or behavior. Ensuring the convergence of these clients' models relies on how closely users collaborate with those with similar patterns or preferences. However, it is generally challenging to quantify similarity under limited knowledge about other users' models given to users in a decentralized network. To cope with this issue, we propose a personalized and fully decentralized FL algorithm, leveraging knowledge distillation techniques to empower each device so as to discern statistical distances between local models. Each client device can enhance its performance without sharing local data by estimating the similarity between two intermediate outputs from feeding local samples as in knowledge distillation. Our empirical studies demonstrate that the proposed algorithm improves the test accuracy of clients in fewer iterations under highly non-independent and identically distributed (non-i.i.d.) data distributions and is beneficial to agents with small datasets, even without the need for a central server.

Pouya Agheli, Nikolaos Pappas, Petar Popovski et al.

This paper studies decision-making for goal-oriented effective communication. We consider an end-to-end status update system where a sensing agent (SA) observes a source, generates and transmits updates to an actuation agent (AA), while the AA takes actions to accomplish a goal at the endpoint. We integrate the push- and pull-based update communication models to obtain a push-and-pull model, which allows the transmission controller at the SA to decide to push an update to the AA and the query controller at the AA to pull updates by raising queries at specific time instances. To gauge effectiveness, we utilize a grade of effectiveness (GoE) metric incorporating updates' freshness, usefulness, and timeliness of actions as qualitative attributes. We then derive effect-aware policies to maximize the expected discounted sum of updates' effectiveness subject to induced costs. The effect-aware policy at the SA considers the potential effectiveness of communicated updates at the endpoint, while at the AA, it accounts for the probabilistic evolution of the source and importance of generated updates. Our results show the proposed push-and-pull model outperforms models solely based on push- or pull-based updates both in terms of efficiency and effectiveness. Additionally, using effect-aware policies at both agents enhances effectiveness compared to periodic and/or probabilistic effect-agnostic policies at either or both agents.

Matteo Zecchin, Marios Kountouris, David Gesbert

Decentralized learning algorithms empower interconnected devices to share data and computational resources to collaboratively train a machine learning model without the aid of a central coordinator. In the case of heterogeneous data distributions at the network nodes, collaboration can yield predictors with unsatisfactory performance for a subset of the devices. For this reason, in this work, we consider the formulation of a distributionally robust decentralized learning task and we propose a decentralized single loop gradient descent/ascent algorithm (AD-GDA) to directly solve the underlying minimax optimization problem. We render our algorithm communication-efficient by employing a compressed consensus scheme and we provide convergence guarantees for smooth convex and non-convex loss functions. Finally, we corroborate the theoretical findings with empirical results that highlight AD-GDA's ability to provide unbiased predictors and to greatly improve communication efficiency compared to existing distributionally robust algorithms.

Giuseppe Serra, Photios A. Stavrou, Marios Kountouris

In this paper, we study the computation of the rate-distortion-perception function (RDPF) for a multivariate Gaussian source under mean squared error (MSE) distortion and, respectively, Kullback-Leibler divergence, geometric Jensen-Shannon divergence, squared Hellinger distance, and squared Wasserstein-2 distance perception metrics. To this end, we first characterize the analytical bounds of the scalar Gaussian RDPF for the aforementioned divergence functions, also providing the RDPF-achieving forward "test-channel" realization. Focusing on the multivariate case, we establish that, for tensorizable distortion and perception metrics, the optimal solution resides on the vector space spanned by the eigenvector of the source covariance matrix. Consequently, the multivariate optimization problem can be expressed as a function of the scalar Gaussian RDPFs of the source marginals, constrained by global distortion and perception levels. Leveraging this characterization, we design an alternating minimization scheme based on the block nonlinear Gauss-Seidel method, which optimally solves the problem while identifying the Gaussian RDPF-achieving realization. Furthermore, the associated algorithmic embodiment is provided, as well as the convergence and the rate of convergence characterization. Lastly, for the "perfect realism" regime, the analytical solution for the multivariate Gaussian RDPF is obtained. We corroborate our results with numerical simulations and draw connections to existing results.

Hyeon Seok Rou, Giuseppe Thadeu Freitas de Abreu, Emil Björnson et al.

Orthogonal frequency-division multiplexing (OFDM) and its static sinusoidal subcarriers have underpinned the 4G and 5G eras, delivering high spectral efficiency and resilience to multipath fading through an efficient multicarrier architecture. However, as future systems move toward doubly dispersive environments driven by high-mobility applications and migration to mmWave/sub-THz bands, the time-invariance assumption underlying OFDM becomes increasingly difficult to maintain, and Doppler-induced degradation becomes prominent. While enhancements such as MIMO, advanced coding, and scheduling provide incremental remedies, they introduce additional overhead, because the sinusoidal subcarrier itself offers no inherent waveform-level robustness to Doppler impairments. Accordingly, two time-frequency spreading philosophies have emerged to improve Doppler resilience by distributing each symbol's energy across both dimensions of the time-frequency plane: (i) 2D isotropic spreading via the delay-Doppler (DD) domain, exemplified by the orthogonal time frequency space (OTFS) family, and (ii) sheared spreading via parameterizable chirps, exemplified by the affine frequency-division multiplexing (AFDM) family. In this article, we examine key considerations for future waveform design across these paradigms and argue that transitioning from the sinusoidal subcarriers of OFDM to the chirp-based subcarriers offers a viable design direction for improving Doppler robustness while retaining much of the mature OFDM infrastructure. This perspective also highlights the suitability of chirp-based waveforms for integrated sensing and communications (ISAC) and their extensibility to emerging physical-layer techniques. Overall, we argue that the transition from sinusoids to chirps is a technically motivated, compelling evolutionary direction for future wireless physical layer design.

Matteo Zecchin, Sangwoo Park, Osvaldo Simeone et al.

Standard Bayesian learning is known to have suboptimal generalization capabilities under misspecification and in the presence of outliers. PAC-Bayes theory demonstrates that the free energy criterion minimized by Bayesian learning is a bound on the generalization error for Gibbs predictors (i.e., for single models drawn at random from the posterior) under the assumption of sampling distributions uncontaminated by outliers. This viewpoint provides a justification for the limitations of Bayesian learning when the model is misspecified, requiring ensembling, and when data is affected by outliers. In recent work, PAC-Bayes bounds -- referred to as PAC$^m$ -- were derived to introduce free energy metrics that account for the performance of ensemble predictors, obtaining enhanced performance under misspecification. This work presents a novel robust free energy criterion that combines the generalized logarithm score function with PAC$^m$ ensemble bounds. The proposed free energy training criterion produces predictive distributions that are able to concurrently counteract the detrimental effects of misspecification -- with respect to both likelihood and prior distribution -- and outliers.

Davit Gogolashvili, Matteo Zecchin, Motonobu Kanagawa et al.

This paper investigates when the importance weighting (IW) correction is needed to address covariate shift, a common situation in supervised learning where the input distributions of training and test data differ. Classic results show that the IW correction is needed when the model is parametric and misspecified. In contrast, recent results indicate that the IW correction may not be necessary when the model is nonparametric and well-specified. We examine the missing case in the literature where the model is nonparametric and misspecified, and show that the IW correction is needed for obtaining the best approximation of the true unknown function for the test distribution. We do this by analyzing IW-corrected kernel ridge regression, covering a variety of settings, including parametric and nonparametric models, well-specified and misspecified settings, and arbitrary weighting functions.

Matteo Zecchin, David Gesbert, Marios Kountouris

Decentralized learning empowers wireless network devices to collaboratively train a machine learning (ML) model relying solely on device-to-device (D2D) communication. It is known that the convergence speed of decentralized optimization algorithms severely depends on the degree of the network connectivity, with denser network topologies leading to shorter convergence time. Consequently, the local connectivity of real world mesh networks, due to the limited communication range of its wireless nodes, undermines the efficiency of decentralized learning protocols, rendering them potentially impracticable. In this work we investigate the role of an unmanned aerial vehicle (UAV), used as flying relay, in facilitating decentralized learning procedures in such challenging conditions. We propose an optimized UAV trajectory, that is defined as a sequence of waypoints that the UAV visits sequentially in order to transfer intelligence across sparsely connected group of users. We then provide a series of experiments highlighting the essential role of UAVs in the context of decentralized learning over mesh networks.

Giuseppe Serra, Photios A. Stavrou, Marios Kountouris

We study the computation of the rate-distortion-perception function (RDPF) for discrete memoryless sources subject to a single-letter average distortion constraint and a perception constraint belonging to the family of $f$-divergences. In this setting, the RDPF forms a convex programming problem for which we characterize optimal parametric solutions. We employ the developed solutions in an alternating minimization scheme, namely Optimal Alternating Minimization (OAM), for which we provide convergence guarantees. Nevertheless, the OAM scheme does not lead to a direct implementation of a generalized Blahut-Arimoto (BA) type of algorithm due to implicit equations in the iteration's structure. To overcome this difficulty, we propose two alternative minimization approaches whose applicability depends on the smoothness of the used perception metric: a Newton-based Alternating Minimization (NAM) scheme, relying on Newton's root-finding method for the approximation of the optimal solution of the iteration, and a Relaxed Alternating Minimization (RAM) scheme, based on relaxing the OAM iterates. We show, by deriving necessary and sufficient conditions, that both schemes guarantee convergence to a globally optimal solution. We also provide sufficient conditions on the distortion and perception constraints, which guarantee that the proposed algorithms converge exponentially fast in the number of iteration steps. We corroborate our theoretical results with numerical simulations and establish connections with existing results.

Jiahui Wei, Marios Kountouris

We extend the Rate-Distortion-Perception (RDP) framework to the Rényi information-theoretic regime, utilizing Sibson's $α$-mutual information to characterize the fundamental limits under distortion and perception constraints. For scalar Gaussian sources, we derive closed-form expressions for the Rényi RDP function, showing that the perception constraint induces a feasible interval for the reproduction variance. Furthermore, we establish a Rényi-generalized version of the Strong Functional Representation Lemma. Our analysis reveals a phase transition in the complexity of optimal functional representations: for $0.5<α< 1$, the coding cost is bounded by the $α$-divergence of order $α+1$, necessitating a codebook with heavy-tailed polynomial decay; conversely, for $α> 1$, the representation collapses to one with finite support, offering new insights into the compression of shared randomness under generalized notions of mutual information.

Ioannis Pitsiorlas, George Arvanitakis, Marios Kountouris

This work introduces a novel method for enhancing confidence in anomaly detection in Intrusion Detection Systems (IDS) through the use of a Variational Autoencoder (VAE) architecture. By developing a confidence metric derived from latent space representations, we aim to improve the reliability of IDS predictions against cyberattacks. Applied to the NSL-KDD dataset, our approach focuses on binary classification tasks to effectively distinguish between normal and malicious network activities. The methodology demonstrates a significant enhancement in anomaly detection, evidenced by a notable correlation of 0.45 between the reconstruction error and the proposed metric. Our findings highlight the potential of employing VAEs for more accurate and trustworthy anomaly detection in network security.

Babacar Toure, Dimitrios Tsilimantos, Omid Esrafilian et al.

Due to their adaptability and mobility, Unmanned Aerial Vehicles (UAVs) are becoming increasingly essential for wireless network services, particularly for data harvesting tasks. In this context, Artificial Intelligence (AI)-based approaches have gained significant attention for addressing UAV path planning tasks in large and complex environments, bridging the gap with real-world deployments. However, many existing algorithms suffer from limited training data, which hampers their performance in highly dynamic environments. Moreover, they often overlook the inherently multi-objective nature of the task, treating it in an overly simplistic manner. To address these limitations, we propose an attention-based Multi-Objective Reinforcement Learning (MORL) architecture that explicitly handles the trade-off between data collection and energy consumption in urban environments, even without prior knowledge of wireless channel conditions. Our method develops a single model capable of adapting to varying trade-off preferences and dynamic scenario parameters without the need for fine-tuning or retraining. Extensive simulations show that our approach achieves substantial improvements in performance, model compactness, sample efficiency, and most importantly, generalization to previously unseen scenarios, outperforming existing RL solutions.

Jiahui Wei, Marios Kountouris

We introduce a Rényi Rate-Distortion-Perception-Privacy (R-RDPP) framework for indirect source coding. A latent source~$S$ is correlated with a private attribute~$U$, and the encoder observes only a noisy view~$X$ such that $(S,U) - X - Y$ holds at the decoder output~$Y$. The communication cost is measured by Sibson's $α$-mutual information $\Ialp$, the privacy leakage by $\Ibeta$, the semantic distortion between $S$ and $Y$, and the realism constraint at the semantic marginal $P_S$. We characterize the scalar Gaussian RDPP tradeoff, revealing that standard privacy metrics inherently penalize legitimate semantic recovery. To resolve this, we introduce a conditional privacy measure that quantifies only the residual leakage. In addition, we refine the achievability bounds for $α> 1$ via the Poisson functional representation. By deriving the exact geometric-mixture distribution of the Poisson index, we obtain exact closed-form expressions for integer-order Rényi entropies and sharper computable bounds in regimes where the resulting expression improves the logarithmic-moment approach.

Jeanne Monnier, Thomas George, Frédéric Guyard et al.

Fairness in machine learning remains challenging due to its ethical complexity, the absence of a universal definition, and the need for context-specific bias metrics. Existing methods still struggle with intersectionality, multiclass settings, and limited flexibility and generality. To address these gaps, we introduce MIFair, a unified framework for bias assessment and mitigation based on mutual information. MIFair provides a flexible metric template and an in-processing mitigation method inspired by the Prejudice Remover, defining group fairness as statistical independence between prediction-derived variables and sensitive attributes. We further strengthen its information-theoretic foundation by establishing equivalences with widely used fairness notions such as independence and separation. MIFair naturally supports intersectionality, complex subgroup structures, and multiclass classification and employs regularization-based training to reduce bias according to the selected metric. Its key advantage is its versatility: it consolidates diverse fairness requirements into a single coherent framework, enabling consistent benchmarking and simplifying practical use. Experiments on real-world tabular and image datasets show that MIFair effectively reduces bias, including previously unaddressed multi-attribute scenarios, while maintaining strong predictive performance across the evaluated settings.

Adnan Shahid, Adrian Kliks, Ahmed Al-Tahmeesschi et al.

This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems. It highlights the development and deployment of Large Telecom Models (LTMs), which are tailored AI models designed to address the complex challenges faced by modern telecom networks. The paper covers a wide range of topics, from the architecture and deployment strategies of LTMs to their applications in network management, resource allocation, and optimization. It also explores the regulatory, ethical, and standardization considerations for LTMs, offering insights into their future integration into telecom infrastructure. The goal is to provide a comprehensive roadmap for the adoption of LTMs to enhance scalability, performance, and user-centric innovation in telecom networks.

Ioannis Pitsiorlas, Argyro Tsantalidou, George Arvanitakis et al.

This study presents a new approach for estimating confidence in machine learning model predictions, specifically in regression tasks utilizing Earth Observation (EO) data, with a particular focus on mosquito abundance (MA) estimation. We take advantage of a Variational AutoEncoder architecture, to derive a confidence metric by the latent space representations of EO datasets. This methodology is pivotal in establishing a correlation between the Euclidean distance in latent representations and the Absolute Error (AE) in individual MA predictions. Our research focuses on EO datasets from the Veneto region in Italy and the Upper Rhine Valley in Germany, targeting areas significantly affected by mosquito populations. A key finding is a notable correlation of 0.46 between the AE of MA predictions and the proposed confidence metric. This correlation signifies a robust, new metric for quantifying the reliability and enhancing the trustworthiness of the AI model's predictions in the context of both EO data analysis and mosquito abundance studies.

Pouya Agheli, Nikolaos Pappas, Marios Kountouris

This paper addresses query scheduling for goal-oriented semantic communication in pull-based status update systems. We consider a system where multiple sensing agents (SAs) observe a source characterized by various attributes and provide updates to multiple actuation agents (AAs), which act upon the received information to fulfill their heterogeneous goals at the endpoint. A hub serves as an intermediary, querying the SAs for updates on observed attributes and maintaining a knowledge base, which is then broadcast to the AAs. The AAs leverage the knowledge to perform their actions effectively. To quantify the semantic value of updates, we introduce a grade of effectiveness (GoE) metric. Furthermore, we integrate cumulative perspective theory (CPT) into the long-term effectiveness analysis to account for risk awareness and loss aversion in the system. Leveraging this framework, we compute effect-aware scheduling policies aimed at maximizing the expected discounted sum of CPT-based total GoE provided by the transmitted updates while complying with a given query cost constraint. To achieve this, we propose a model-based solution based on dynamic programming and model-free solutions employing state-of-the-art deep reinforcement learning (DRL) algorithms. Our findings demonstrate that effect-aware scheduling significantly enhances the effectiveness of communicated updates compared to benchmark scheduling methods, particularly in settings with stringent cost constraints where optimal query scheduling is vital for system performance and overall effectiveness.

Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou et al.

Federated learning (FL) is a widely used and impactful distributed optimization framework that achieves consensus through averaging locally trained models. While effective, this approach may not align well with Bayesian inference, where the model space has the structure of a distribution space. Taking an information-geometric perspective, we reinterpret FL aggregation as the problem of finding the barycenter of local posteriors using a prespecified divergence metric, minimizing the average discrepancy across clients. This perspective provides a unifying framework that generalizes many existing methods and offers crisp insights into their theoretical underpinnings. We then propose BA-BFL, an algorithm that retains the convergence properties of Federated Averaging in non-convex settings. In non-independent and identically distributed scenarios, we conduct extensive comparisons with statistical aggregation techniques, showing that BA-BFL achieves performance comparable to state-of-the-art methods while offering a geometric interpretation of the aggregation phase. Additionally, we extend our analysis to Hybrid Bayesian Deep Learning, exploring the impact of Bayesian layers on uncertainty quantification and model calibration.

Mehrdad Salimnejad, Anthony Ephremides, Marios Kountouris et al.

This paper studies efficient data management and timely information dissemination for real-time monitoring of an $N$-state Markov process, enabling accurate state estimation and reliable actuation decisions. First, we analyze the Age of Incorrect Information (AoII) and derive closed-form expressions for its time average under several scheduling policies, including randomized stationary, change-aware randomized stationary, semantics-aware randomized stationary, and threshold-aware randomized stationary policies. We then formulate and solve constrained optimization problems to minimize the average AoII under a time-averaged sampling action constraint, and compare the resulting optimal sampling and transmission policies to identify the conditions under which each policy is most effective. We further show that directly using reconstructed states for actuation can degrade system performance, especially when the receiver is uncertain about the state estimate or when actuation is costly. To address this issue, we introduce a cost function, termed the Cost of Actions under Uncertainty (CoAU), which determines when the actuator should take correct actions and avoid incorrect ones when the receiver is uncertain about the reconstructed source state. We propose a randomized actuation policy and derive a closed-form expression for the probability of taking no incorrect action. Finally, we formulate an optimization problem to find the optimal randomized actuation policy that maximizes this probability. The results show that the resulting policy substantially reduces incorrect actuator actions.

Niccolò Zanieri, Marios Kountouris

Entanglement fidelity quantifies how well a quantum channel preserves the correlations between a transmitted system and an inaccessible reference system. We derive closed-form expressions for the entanglement fidelity associated with several standard quantum noise models, including the random Pauli-X, dephasing, depolarizing, Werner-Holevo, generalized Pauli (Weyl), and amplitude-damping channels. For each model, we express the entanglement fidelity in terms of a general input density operator $ρ$, using Schumacher's Kraus-operator approach, which provides a channel-agnostic recipe applicable to any completely positive trace-preserving (CPTP) map with a finite Kraus representation. We then specialize to a communication scenario in which the source emits a two-letter parametric alphabet, thereby making explicit the dependence of entanglement preservation on both channel and source parameters. The resulting expressions enable direct comparisons of channel performance and rankings for representative families of input states, including common qubit states.

Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou et al.

Bayesian Federated Learning (BFL) combines uncertainty modeling with decentralized training, enabling the development of personalized and reliable models under data heterogeneity and privacy constraints. Existing approaches typically rely on Markov Chain Monte Carlo (MCMC) sampling or variational inference, often incorporating personalization mechanisms to better adapt to local data distributions. In this work, we propose an information-geometric projection framework for personalization in parametric BFL. By projecting the global model onto a neighborhood of the user's local model, our method enables a tunable trade-off between global generalization and local specialization. Under mild assumptions, we show that this projection step is equivalent to computing a barycenter on the statistical manifold, allowing us to derive closed-form solutions and achieve cost-free personalization. We apply the proposed approach to a variational learning setup using the Improved Variational Online Newton (IVON) optimizer and extend its application to general aggregation schemes in BFL. Empirical evaluations under heterogeneous data distributions confirm that our method effectively balances global and local performance with minimal computational overhead.

Ilias Chatzistefanidis, Navid Nikaein, Andrea Leone et al.

Next-generation mobile networks must reconcile the often-conflicting goals of multiple service owners. However, today's network slice controllers remain rigid, policy-bound, and unaware of the business context. We introduce Agoran Service and Resource Broker (SRB), an agentic marketplace that brings stakeholders directly into the operational loop. Inspired by the ancient Greek agora, Agoran distributes authority across three autonomous AI branches: a Legislative branch that answers compliance queries using retrieval-augmented Large Language Models (LLMs); an Executive branch that maintains real-time situational awareness through a watcher-updated vector database; and a Judicial branch that evaluates each agent message with a rule-based Trust Score, while arbitrating LLMs detect malicious behavior and apply real-time incentives to restore trust. Stakeholder-side Negotiation Agents and the SRB-side Mediator Agent negotiate feasible, Pareto-optimal offers produced by a multi-objective optimizer, reaching a consensus intent in a single round, which is then deployed to Open and AI RAN controllers. Deployed on a private 5G testbed and evaluated with realistic traces of vehicle mobility, Agoran achieved significant gains: (i) a 37% increase in throughput of eMBB slices, (ii) a 73% reduction in latency of URLLC slices, and concurrently (iii) an end-to-end 8.3% saving in PRB usage compared to a static baseline. An 1B-parameter Llama model, fine-tuned for five minutes on 100 GPT-4 dialogues, recovers approximately 80% of GPT-4.1's decision quality, while operating within 6 GiB of memory and converging in only 1.3 seconds. These results establish Agoran as a concrete, standards-aligned path toward ultra-flexible, stakeholder-centric 6G networks. A live demo is presented https://www.youtube.com/watch?v=h7vEyMu2f5w\&ab_channel=BubbleRAN.

Jaiprakash Nagar, Zheng Chen, Marios Kountouris et al.

This paper addresses decentralized stochastic gradient descent (D-SGD) over resource-constrained networks by introducing node-based and link-based scheduling strategies to enhance communication efficiency. In each iteration of the D-SGD algorithm, only a few disjoint subsets of nodes or links are randomly activated, subject to a given communication cost constraint. We propose a novel importance metric based on information entropy to determine node and link scheduling probabilities. We validate the effectiveness of our approach through extensive simulations, comparing it against state-of-the-art methods, including betweenness centrality (BC) for node scheduling and \textit{MATCHA} for link scheduling. The results show that our method consistently outperforms the BC-based method in the node scheduling case, achieving faster convergence with up to 60\% lower communication budgets. At higher communication budgets (above 60\%), our method maintains comparable or superior performance. In the link scheduling case, our method delivers results that are superior to or on par with those of \textit{MATCHA}.

Ioannis Pitsiorlas, Nour Jamoussi, Marios Kountouris

This work introduces a novel methodology for assessing catastrophic forgetting (CF) in continual learning. We propose a new conformal prediction (CP)-based metric, termed the Conformal Prediction Confidence Factor (CPCF), to quantify and evaluate CF effectively. Our framework leverages adaptive CP to estimate forgetting by monitoring the model's confidence on previously learned tasks. This approach provides a dynamic and practical solution for monitoring and measuring CF of previous tasks as new ones are introduced, offering greater suitability for real-world applications. Experimental results on four benchmark datasets demonstrate a strong correlation between CPCF and the accuracy of previous tasks, validating the reliability and interpretability of the proposed metric. Our results highlight the potential of CPCF as a robust and effective tool for assessing and understanding CF in dynamic learning environments.

Eunjeong Jeong, Marios Kountouris

Recent developments and emerging use cases, such as smart Internet of Things (IoT) and Edge AI, have sparked considerable interest in the training of neural networks over fully decentralized (serverless) networks. One of the major challenges of decentralized learning is to ensure stable convergence without resorting to strong assumptions applied for each agent regarding data distributions or updating policies. To address these issues, we propose DRACO, a novel method for decentralized asynchronous Stochastic Gradient Descent (SGD) over row-stochastic gossip wireless networks by leveraging continuous communication. Our approach enables edge devices within decentralized networks to perform local training and model exchanging along a continuous timeline, thereby eliminating the necessity for synchronized timing. The algorithm also features a specific technique of decoupling communication and computation schedules, which empowers complete autonomy for all users and manageable instructions for stragglers. Through a comprehensive convergence analysis, we highlight the advantages of asynchronous and autonomous participation in decentralized optimization. Our numerical experiments corroborate the efficacy of the proposed technique.

Yuchang Sun, Marios Kountouris, Jun Zhang

Federated learning (FL) has attracted vivid attention as a privacy-preserving distributed learning framework. In this work, we focus on cross-silo FL, where clients become the model owners after training and are only concerned about the model's generalization performance on their local data. Due to the data heterogeneity issue, asking all the clients to join a single FL training process may result in model performance degradation. To investigate the effectiveness of collaboration, we first derive a generalization bound for each client when collaborating with others or when training independently. We show that the generalization performance of a client can be improved only by collaborating with other clients that have more training data and similar data distribution. Our analysis allows us to formulate a client utility maximization problem by partitioning clients into multiple collaborating groups. A hierarchical clustering-based collaborative training (HCCT) scheme is then proposed, which does not need to fix in advance the number of groups. We further analyze the convergence of HCCT for general non-convex loss functions which unveils the effect of data similarity among clients. Extensive simulations show that HCCT achieves better generalization performance than baseline schemes, whereas it degenerates to independent training and conventional FL in specific scenarios.

Apostolos Avranas, Marios Kountouris

The conventional, widely used treatment of deep learning models as black boxes provides limited or no insights into the mechanisms that guide neural network decisions. Significant research effort has been dedicated to building interpretable models to address this issue. Most efforts either focus on the high-level features associated with the last layers, or attempt to interpret the output of a single layer. In this paper, we take a novel approach to enhance the transparency of the function of the whole network. We propose a neural network architecture for classification, in which the information that is relevant to each class flows through specific paths. These paths are designed in advance before training leveraging coding theory and without depending on the semantic similarities between classes. A key property is that each path can be used as an autonomous single-purpose model. This enables us to obtain, without any additional training and for any class, a lightweight binary classifier that has at least $60\%$ fewer parameters than the original network. Furthermore, our coding theory based approach allows the neural network to make early predictions at intermediate layers during inference, without requiring its full evaluation. Remarkably, the proposed architecture provides all the aforementioned properties while improving the overall accuracy. We demonstrate these properties on a slightly modified ResNeXt model tested on CIFAR-10/100 and ImageNet-1k.

Eunjeong Jeong, Matteo Zecchin, Marios Kountouris

Decentralized learning enables edge users to collaboratively train models by exchanging information via device-to-device communication, yet prior works have been limited to wireless networks with fixed topologies and reliable workers. In this work, we propose an asynchronous decentralized stochastic gradient descent (DSGD) algorithm, which is robust to the inherent computation and communication failures occurring at the wireless network edge. We theoretically analyze its performance and establish a non-asymptotic convergence guarantee. Experimental results corroborate our analysis, demonstrating the benefits of asynchronicity and outdated gradient information reuse in decentralized learning over unreliable wireless networks.

André N. Barreto, Stefan Köpsell, Arsenia Chorti et al.

Imagine interconnected objects with embedded artificial intelligence (AI), empowered to sense the environment, see it, hear it, touch it, interact with it, and move. As future networks of intelligent objects come to life, tremendous new challenges arise for security, but also new opportunities, allowing to address current, as well as future, pressing needs. In this paper we put forward a roadmap towards the realization of a new security paradigm that we articulate as intelligent context-aware security. The premise of this roadmap is that sensing and advanced AI will enable context awareness, which in turn can drive intelligent security mechanisms, such as adaptation and automation of security controls. This concept not only provides immediate answers to burning open questions, in particular with respect to non-functional requirements, such as energy or latency constraints, heterogeneity of radio frequency (RF) technologies and long life span of deployed devices, but also, more importantly, offers a viable answer to scalability by allowing such constraints to be met even in massive connectivity regimes. Furthermore, the proposed roadmap has to be designed ethically, by explicitly placing privacy concerns at its core. The path towards this vision and some of the challenges along the way are discussed in this contribution.

Matteo Zecchin, Mahdi Boloursaz Mashhadi, Mikolaj Jankowski et al.

Efficient millimeter wave (mmWave) beam selection in vehicle-to-infrastructure (V2I) communication is a crucial yet challenging task due to the narrow mmWave beamwidth and high user mobility. To reduce the search overhead of iterative beam discovery procedures, contextual information from light detection and ranging (LIDAR) sensors mounted on vehicles has been leveraged by data-driven methods to produce useful side information. In this paper, we propose a lightweight neural network (NN) architecture along with the corresponding LIDAR preprocessing, which significantly outperforms previous works. Our solution comprises multiple novelties that improve both the convergence speed and the final accuracy of the model. In particular, we define a novel loss function inspired by the knowledge distillation idea, introduce a curriculum training approach exploiting line-of-sight (LOS)/non-line-of-sight (NLOS) information, and we propose a non-local attention module to improve the performance for the more challenging NLOS cases. Simulation results on benchmark datasets show that, utilizing solely LIDAR data and the receiver position, our NN-based beam selection scheme can achieve 79.9% throughput of an exhaustive beam sweeping approach without any beam search overhead and 95% by searching among as few as 6 beams. In a typical mmWave V2I scenario, our proposed method considerably reduces the beam search time required to achieve a desired throughput, in comparison with the inverse fingerprinting and hierarchical beam selection schemes.

Apostolos Avranas, Marios Kountouris, Philippe Ciblat

The problem of resource constrained scheduling in a dynamic and heterogeneous wireless setting is considered here. In our setup, the available limited bandwidth resources are allocated in order to serve randomly arriving service demands, which in turn belong to different classes in terms of payload data requirement, delay tolerance, and importance/priority. In addition to heterogeneous traffic, another major challenge stems from random service rates due to time-varying wireless communication channels. Various approaches for scheduling and resource allocation can be used, ranging from simple greedy heuristics and constrained optimization to combinatorics. Those methods are tailored to specific network or application configuration and are usually suboptimal. To this purpose, we resort to deep reinforcement learning (DRL) and propose a distributional Deep Deterministic Policy Gradient (DDPG) algorithm combined with Deep Sets to tackle the aforementioned problem. Furthermore, we present a novel way to use a Dueling Network, which leads to further performance improvement. Our proposed algorithm is tested on both synthetic and real data, showing consistent gains against state-of-the-art conventional methods from combinatorics, optimization, and scheduling metrics.

Matteo Zecchin, David Gesbert, Marios Kountouris

In the context of wireless networking, it was recently shown that multiple DNNs can be jointly trained to offer a desired collaborative behaviour capable of coping with a broad range of sensing uncertainties. In particular, it was established that DNNs can be used to derive policies that are robust with respect to the information noise statistic affecting the local information (e.g. CSI in a wireless network) used by each agent (e.g. transmitter) to make its decision. While promising, a major challenge in the implementation of such method is that information noise statistics may differ from agent to agent and, more importantly, that such statistics may not be available at the time of training or may evolve over time, making burdensome retraining necessary. This situation makes it desirable to devise a "universal" machine learning model, which can be trained once for all so as to allow for decentralized cooperation in any future feedback noise environment. With this goal in mind, we propose an architecture inspired from the well-known Mixture of Experts (MoE) model, which was previously used for non-linear regression and classification tasks in various contexts, such as computer vision and speech recognition. We consider the decentralized power control problem as an example to showcase the validity of the proposed model and to compare it against other power control algorithms. We show the ability of the so called Team-DMoE model to efficiently track time-varying statistical scenarios.