Qianqian Yang

Yuhao Chen, Yuxuan Yan, Qianqian Yang et al.

Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks. Nonetheless, it is challenging to deploy and fine-tune LLMs on mobile edge devices with limited computing, memory, and energy budgets. In this paper, we propose Confidant, a multi-backend collaborative training framework for customizing state-of-the-art LLMs on commodity mobile devices like smartphones. Confidant partitions an LLM into several sub-models so that each fits into a mobile device's memory. A pipeline parallel training mechanism is further developed to ensure fast and efficient distributed training. In addition, we propose a novel backend scheduler to allocate different attention heads to heterogeneous compute hardware, including mobile CPU and GPUs, to maximize the compute resource utilization on each edge device. Our preliminary experimental results show that Confidant achieves at most 45.3% memory reduction and 8.03x inference speedup in practical settings.

Yuhao Chen, Qianqian Yang, Zhiguo Shi et al.

In recent years, semantic communication has been a popular research topic for its superiority in communication efficiency. As semantic communication relies on deep learning to extract meaning from raw messages, it is vulnerable to attacks targeting deep learning models. In this paper, we introduce the model inversion eavesdropping attack (MIEA) to reveal the risk of privacy leaks in the semantic communication system. In MIEA, the attacker first eavesdrops the signal being transmitted by the semantic communication system and then performs model inversion attack to reconstruct the raw message, where both the white-box and black-box settings are considered. Evaluation results show that MIEA can successfully reconstruct the raw message with good quality under different channel conditions. We then propose a defense method based on random permutation and substitution to defend against MIEA in order to achieve secure semantic communication. Our experimental results demonstrate the effectiveness of the proposed defense method in preventing MIEA.

Yulin Shao, Chenghong Bian, Li Yang et al.

Acquisition and processing of point clouds (PCs) is a crucial enabler for many emerging applications reliant on 3D spatial data, such as robot navigation, autonomous vehicles, and augmented reality. In most scenarios, PCs acquired by remote sensors must be transmitted to an edge server for fusion, segmentation, or inference. Wireless transmission of PCs not only puts on increased burden on the already congested wireless spectrum, but also confronts a unique set of challenges arising from the irregular and unstructured nature of PCs. In this paper, we meticulously delineate these challenges and offer a comprehensive examination of existing solutions while candidly acknowledging their inherent limitations. In response to these intricacies, we proffer four pragmatic solution frameworks, spanning advanced techniques, hybrid schemes, and distributed data aggregation approaches. In doing so, our goal is to chart a path toward efficient, reliable, and low-latency wireless PC transmission.

Shangzhuo Xie, Qianqian Yang

Point cloud analysis has evolved with diverse network architectures, while existing works predominantly focus on introducing novel structural designs. However, conventional point-based architectures - processing raw points through sequential sampling, grouping, and feature extraction layers - demonstrate underutilized potential. We notice that substantial performance gains can be unlocked through strategic module integration rather than structural modifications. In this paper, we propose the Grouping-Feature Coordination Module (GF-Core), a lightweight separable component that simultaneously regulates both grouping layer and feature extraction layer to enable more nuanced feature aggregation. Besides, we introduce a self-supervised pretraining strategy specifically tailored for point-based inputs to enhance model robustness in complex point cloud analysis scenarios. On ModelNet40 dataset, our method elevates baseline networks to 94.0% accuracy, matching advanced frameworks' performance while preserving architectural simplicity. On three variants of the ScanObjectNN dataset, we obtain improvements of 2.96%, 6.34%, and 6.32% respectively.

Yuhao Chen, Qianqian Yang, Shibo He et al.

With the increased penetration and proliferation of Internet of Things (IoT) devices, there is a growing trend towards distributing the power of deep learning (DL) across edge devices rather than centralizing it in the cloud. This development enables better privacy preservation, real-time responses, and user-specific models. To deploy deep and complex models to edge devices with limited resources, model partitioning of deep neural networks (DNN) model is necessary, and has been widely studied. However, most of the existing literature only considers distributing the inference model while still relying centralized cloud infrastructure to generate this model through training. In this paper, we propose FTPipeHD, a novel DNN training framework that trains DNN models across distributed heterogeneous devices with fault tolerance mechanism. To accelerate the training with time-varying computing power of each device, we optimize the partition points dynamically according to real-time computing capacities. We also propose a novel weight redistribution approach that replicates the weights to both the neighboring nodes and the central node periodically, which combats the failure of multiple devices during training while incurring limited communication cost. Our numerical results demonstrate that FTPipeHD is 6.8x faster in training than the state of the art method when the computing capacity of the best device is 10x greater than the worst one. It is also shown that the proposed method is able to accelerate the training even with the existence of device failures.

Shunjie Dong, Qianqian Yang, Yu Fu et al.

The novel 2019 Coronavirus (COVID-19) infection has spread world widely and is currently a major healthcare challenge around the world. Chest Computed Tomography (CT) and X-ray images have been well recognized to be two effective techniques for clinical COVID-19 disease diagnoses. Due to faster imaging time and considerably lower cost than CT, detecting COVID-19 in chest X-ray (CXR) images is preferred for efficient diagnosis, assessment and treatment. However, considering the similarity between COVID-19 and pneumonia, CXR samples with deep features distributed near category boundaries are easily misclassified by the hyper-planes learned from limited training data. Moreover, most existing approaches for COVID-19 detection focus on the accuracy of prediction and overlook the uncertainty estimation, which is particularly important when dealing with noisy datasets. To alleviate these concerns, we propose a novel deep network named {\em RCoNet$^k_s$} for robust COVID-19 detection which employs {\em Deformable Mutual Information Maximization} (DeIM), {\em Mixed High-order Moment Feature} (MHMF) and {\em Multi-expert Uncertainty-aware Learning} (MUL). With DeIM, the mutual information (MI) between input data and the corresponding latent representations can be well estimated and maximized to capture compact and disentangled representational characteristics. Meanwhile, MHMF can fully explore the benefits of using high-order statistics and extract discriminative features of complex distributions in medical imaging. Finally, MUL creates multiple parallel dropout networks for each CXR image to evaluate uncertainty and thus prevent performance degradation caused by the noise in the data.

Mahdi Boloursaz Mashhadi, Qianqian Yang, Deniz Gunduz

Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to achieve spatial diversity and multiplexing gains. In a frequency division duplex (FDD) multiuser massive MIMO network, each user needs to compress and feedback its downlink CSI to the BS. The CSI overhead scales with the number of antennas, users and subcarriers, and becomes a major bottleneck for the overall spectral efficiency. In this paper, we propose a deep learning (DL)-based CSI compression scheme, called DeepCMC, composed of convolutional layers followed by quantization and entropy coding blocks. In comparison with previous DL-based CSI reduction structures, DeepCMC proposes a novel fully-convolutional neural network (NN) architecture, with residual layers at the decoder, and incorporates quantization and entropy coding blocks into its design. DeepCMC is trained to minimize a weighted rate-distortion cost, which enables a trade-off between the CSI quality and its feedback overhead. Simulation results demonstrate that DeepCMC outperforms the state of the art CSI compression schemes in terms of the reconstruction quality of CSI for the same compression rate. We also propose a distributed version of DeepCMC for a multi-user MIMO scenario to encode and reconstruct the CSI from multiple users in a distributed manner. Distributed DeepCMC not only utilizes the inherent CSI structures of a single MIMO user for compression, but also benefits from the correlations among the channel matrices of nearby users to further improve the performance in comparison with DeepCMC. We also propose a reduced-complexity training method for distributed DeepCMC, allowing to scale it to multiple users, and suggest a cluster-based distributed DeepCMC approach for practical implementation.

Mahdi Boloursaz Mashhadi, Qianqian Yang, Deniz Gunduz

Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to better utilize the available spatial diversity and multiplexing gains. However, in a frequency division duplex (FDD) massive MIMO system, CSI feedback overhead degrades the overall spectral efficiency. Convolutional neural network (CNN)-based CSI feedback compression schemes has received a lot of attention recently due to significant improvements in compression efficiency; however, they still require reliable feedback links to convey the compressed CSI information to the BS. Instead, we propose here a CNN-based analog feedback scheme, called AnalogDeepCMC, which directly maps the downlink CSI to uplink channel input. Corresponding noisy channel outputs are used by another CNN to reconstruct the DL channel estimate. Not only the proposed outperforms existing digital CSI feedback schemes in terms of the achievable downlink rate, but also simplifies the operation as it does not require explicit quantization, coding and modulation, and provides a low-latency alternative particularly in rapidly changing MIMO channels, where the CSI needs to be estimated and fed back periodically.

Qianqian Yang, Mahdi Boloursaz Mashhadi, Deniz Gündüz

Coded caching provides significant gains over conventional uncoded caching by creating multicasting opportunities among distinct requests. Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to better utilize the available spatial diversity and multiplexing gains. However, in a frequency division duplex (FDD) massive MIMO system, the huge CSI feedback overhead becomes restrictive and degrades the overall spectral efficiency. In this paper, we propose a deep learning based channel state matrix compression scheme, called DeepCMC, composed of convolutional layers followed by quantization and entropy coding blocks. In comparison with previous works, the main contributions of DeepCMC are two-fold: i) DeepCMC is fully convolutional, and it can be used in a wide range of scenarios with various numbers of sub-channels and transmit antennas; ii) DeepCMC includes quantization and entropy coding blocks and minimizes a cost function that accounts for both the rate of compression and the reconstruction quality of the channel matrix at the BS. Simulation results demonstrate that DeepCMC significantly outperforms the state of the art compression schemes in terms of the reconstruction quality of the channel state matrix for the same compression rate, measured in bits per channel dimension.

Qianqian Yang, Pablo Piantanida, Deniz Gündüz

The muti-layer information bottleneck (IB) problem, where information is propagated (or successively refined) from layer to layer, is considered. Based on information forwarded by the preceding layer, each stage of the network is required to preserve a certain level of relevance with regards to a specific hidden variable, quantified by the mutual information. The hidden variables and the source can be arbitrarily correlated. The optimal trade-off between rates of relevance and compression (or complexity) is obtained through a single-letter characterization, referred to as the rate-relevance region. Conditions of successive refinabilty are given. Binary source with BSC hidden variables and binary source with BSC/BEC mixed hidden variables are both proved to be successively refinable. We further extend our result to Guassian models. A counterexample of successive refinability is also provided.