Lorenzo Cazzella;Marouan Mizmizi;Dario Tagliaferri;Damiano Badini;Matteo Matteucci;Umberto Spagnolini
{"title":"Deep Learning-Based Target-to-User Association in Integrated Sensing and Communication Systems","authors":"Lorenzo Cazzella;Marouan Mizmizi;Dario Tagliaferri;Damiano Badini;Matteo Matteucci;Umberto Spagnolini","doi":"10.1109/JSTSP.2024.3438128","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3438128","url":null,"abstract":"In Integrated Sensing and Communication (ISAC) systems, matching the radar targets with communication user equipments (UEs) is functional to several communication tasks, such as proactive handover and beam prediction. In this paper, we consider a radar-assisted communication system where a base station (BS) is equipped with a multiple-input-multiple-output (MIMO) radar that has a double aim: \u0000<italic>i)</i>\u0000 associate vehicular radar targets to vehicular equipments (VEs) in the communication beamspace and \u0000<italic>ii)</i>\u0000 predict the beamforming vector for each VE from radar data. The proposed target-to-user (T2U) association consists of two stages. First, vehicular radar targets are detected from range-angle images, and, for each, a beamforming vector is estimated. Then, the inferred per-target beamforming vectors are matched with the ones utilized at the BS for communication to perform target-to-user (T2U) association. Joint multi-target detection and beam inference is obtained by modifying the you only look once (YOLO) model, which is trained over simulated range-angle radar images. Simulation results over different urban vehicular mobility scenarios show that the proposed T2U method provides a probability of correct association that increases with the size of the BS antenna array, highlighting the respective increase of the separability of the VEs in the beamspace. Moreover, we show that the modified YOLO architecture can effectively perform both beam prediction and radar target detection, with similar performance in mean average precision on the latter over different antenna array sizes.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"18 5","pages":"886-900"},"PeriodicalIF":8.7,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Computational Offloading in Semantic-Aware Cloud-Edge-End Collaborative Networks","authors":"Zelin Ji;Zhijin Qin","doi":"10.1109/JSTSP.2024.3433387","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3433387","url":null,"abstract":"The trend of massive connectivity pushes forward the explosive growth of end devices. The emergence of various applications has prompted a demand for pervasive connectivity and more efficient computing paradigms. On the other hand, the lack of computational capacity of the end devices restricts the implementation of the intelligent applications, and becomes a bottleneck of the multiple access for supporting massive connectivity. Mobile cloud computing (MCC) and mobile edge computing (MEC) techniques enable end devices to offload local computation-intensive tasks to servers by networks. In this paper, we consider the cloud-edge-end collaborative networks to utilize distributed computing resources. Furthermore, we apply task-oriented semantic communications to tackle the fast-varying channel between the end devices and MEC servers and reduce the communication cost. To minimize long-term energy consumption on constraints queue stability and computational delay, a Lyapunov-guided deep reinforcement learning hybrid (DRLH) framework is proposed to solve the mixed integer non-linear programming (MINLP) problem. The long-term energy consumption minimization problem is transformed into the deterministic problem in each time frame. The DRLH framework integrates a model-free deep reinforcement learning algorithm with a model-based mathematical optimization algorithm to mitigate computational complexity and leverage the scenario information, so that improving the convergence performance. Numerical results demonstrate that the proposed DRLH framework achieves near-optimal performance on energy consumption while stabilizing all queues.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"18 7","pages":"1235-1248"},"PeriodicalIF":8.7,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Unstructured Pruning and Low Rank Factorisation of Self-Supervised Pre-Trained Speech Models","authors":"Haoyu Wang;Wei-Qiang Zhang","doi":"10.1109/JSTSP.2024.3433616","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3433616","url":null,"abstract":"Self-supervised pre-trained speech models require significant memory and computational resources, limiting their applicability to many speech tasks. Unstructured pruning is a compression method that can achieve minimal performance degradation, while the resulting sparse matrix mandates special hardware or computational operators for acceleration. In this study, we propose a novel approach that leverages the potential low-rank structures of the unstructured sparse matrices by applying truncated singular value decomposition (SVD), thus converting them into parameter-efficient dense models. Moreover, we introduce nuclear norm regularisation to ensure lower rank and a learnable singular value selection strategy to determine the approximate truncation rate for each matrix. Experiments on multiple speech tasks demonstrate that the proposed method can convert an unstructured sparse model into a light-weight and hardware-friendly dense model with comparable or superior performance.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"18 6","pages":"1046-1058"},"PeriodicalIF":8.7,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kevin Riou;Kaiwen Dong;Kevin Subrin;Patrick Le Callet
{"title":"Reinforcement Learning Based Tactile Sensing for Active Point Cloud Acquisition, Recognition and Localization","authors":"Kevin Riou;Kaiwen Dong;Kevin Subrin;Patrick Le Callet","doi":"10.1109/JSTSP.2024.3431203","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3431203","url":null,"abstract":"Traditional passive point cloud acquisition systems, such as lidars or stereo cameras, can be impractical in real-life and industrial use cases. Firstly, some extreme environments may preclude the use of these sensors. Secondly, they capture information from the entire scene instead of focusing on areas relevant to the end task, such as object recognition and localization. In contrast, we propose to train a Reinforcement Learning (RL) agent with dual objectives: i) control a robot equipped with a tactile (or laser) sensor to iteratively collect a few relevant points from the scene, and ii) recognize and localize objects from the sparse point cloud which has been collected. The iterative point sampling strategy, referred to as an active sampling strategy, is jointly trained with the classifier and the pose estimator to ensure efficient exploration that focuses on areas relevant to the recognition task. To achive these two objectives, we introduce three RL reward terms: classification, exploration, and pose estimation rewards. These rewards serve the purpose of offering guidance and supervision in their respective domain, allowing us to delve into their individual impacts and contributions. We compare the proposed framework to both active sampling strategies and passive hard-coded sampling strategies coupled with state-of-the-art point cloud classifiers. Furthermore, we evaluate our framework in realistic scenarios, considering realistic and similar objects, as well as accounting for uncertainty in the object's position in the workspace.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"18 3","pages":"299-311"},"PeriodicalIF":8.7,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142137576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Knowing When to Stop: Delay-Adaptive Spiking Neural Network Classifiers With Reliability Guarantees","authors":"Jiechen Chen;Sangwoo Park;Osvaldo Simeone","doi":"10.1109/JSTSP.2024.3431996","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3431996","url":null,"abstract":"Spiking neural networks (SNNs) process time-series data via internal event-driven neural dynamics. The energy consumption of an SNN depends on the number of spikes exchanged between neurons over the course of the input presentation. Typically, decisions are produced after the entire input sequence has been processed. This results in latency and energy consumption levels that are fairly uniform across inputs. However, as explored in recent work, SNNs can produce an early decision when the SNN model is sufficiently “confident”, adapting delay and energy consumption to the difficulty of each example. Existing techniques are based on heuristic measures of confidence that do not provide reliability guarantees, potentially exiting too early. In this paper, we introduce a novel delay-adaptive SNN-based inference methodology that, wrapping around any pre-trained SNN classifier, provides guaranteed reliability for the decisions produced at input-dependent stopping times. The approach, dubbed <italic>SpikeCP</i>, leverages tools from conformal prediction (CP). It entails minimal complexity increase as compared to the underlying SNN, requiring only additional thresholding and counting operations at run time. SpikeCP is also extended to integrate a CP-aware training phase that targets delay performance. Variants of CP based on alternative confidence correction schemes, from Bonferroni to Simes, are explored, and extensive experiments are described using the MNIST-DVS data set, DVS128 Gesture dataset, and CIFAR-10 dataset.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 1","pages":"88-102"},"PeriodicalIF":8.7,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hongwei Hou;Xuan He;Tianhao Fang;Xinping Yi;Wenjin Wang;Shi Jin
{"title":"Beam-Delay Domain Channel Estimation for mmWave XL-MIMO Systems","authors":"Hongwei Hou;Xuan He;Tianhao Fang;Xinping Yi;Wenjin Wang;Shi Jin","doi":"10.1109/JSTSP.2024.3431919","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3431919","url":null,"abstract":"This paper investigates the uplink channel estimation of the millimeter-wave (mmWave) extremely large-scale multiple-input-multiple-output (XL-MIMO) communication system in the beam-delay domain, taking into account the near-field and beam-squint effects due to the transmission bandwidth and array aperture growth. Specifically, we model spatial-frequency domain channels in the beam-delay domain to explore inter-antenna and inter-subcarrier correlations. Within this model, the frequency-dependent hybrid-field beam domain steering vectors are introduced to describe the near-field and beam-squint effects. The independent and non-identically distributed Bernoulli-Gaussian models with unknown prior hyperparameters are employed to capture the sparsity in the beam-delay domain, posing a challenge for channel estimation. Under the constrained Bethe free energy minimization framework, we design different structures and constraints on trial beliefs to develop hybrid message passing (HMP) algorithms, thus achieving efficient joint estimation of beam-delay domain channel and prior hyperparameters. To further improve the model accuracy, the multidimensional grid point perturbation (MDGPP)-based representation is presented, which assigns individual perturbation parameters to each multidimensional discrete grid. By treating the MDGPP parameters as unknown hyperparameters, we propose the two-stage HMP algorithm for MDGPP-based channel estimation, where the output of the initial stage is pruned for the refinement stage to reduce the computational complexity. Numerical simulations demonstrate the significant superiority of the proposed algorithm over benchmarks with both near-field and beam-squint effects.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"18 4","pages":"646-661"},"PeriodicalIF":8.7,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xuxi Chen;Tianlong Chen;Yu Cheng;Weizhu Chen;Ahmed Hassan Awadallah;Zhangyang Wang
{"title":"One is Not Enough: Parameter-Efficient Fine-Tuning With Multiplicative Sparse Factorization","authors":"Xuxi Chen;Tianlong Chen;Yu Cheng;Weizhu Chen;Ahmed Hassan Awadallah;Zhangyang Wang","doi":"10.1109/JSTSP.2024.3431927","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3431927","url":null,"abstract":"Fine-tuning gigantic pre-trained models is becoming a canonical paradigm in natural language processing. Unfortunately, as the pre-trained models grow larger, even the conventional fine-tuning becomes prohibitively resource-consuming. That motivates the recent surge of <italic>parameter-efficient</i> fine-tuning methods by selectively updating a small portion of model parameters. Existing methods either customize add-on modules (e.g., adapter, prompter), or refer to weight parameter decomposition which relies on strong structural assumptions (e.g., sparse or low-rank updates) and ad-hoc pre-defined structure parameters (e.g., layerwise sparsities, or the intrinsic rank). Extending the latter line of work, this paper proposes a new weight structured decomposition scheme for parameter-efficient fine-tuning, that is designed to be (i) <italic>flexible</i>, covering a much broader matrix family, with sparse or low-rank matrices as special cases; (ii) <italic>(nearly) hyperparameter-free</i>, requiring only a global parameter budget as input. This new scheme, dubbed <bold>AutoSparse</b>, meets the two goals by factorizing each layer's weight update into a product of multiple sparse matrix factors. Notably, the sparsity levels of all those matrices are <italic>automatically allocated</i> (without adopting any heuristic or ad-hoc tuning), through one holistic budget-constrained optimization. It can be solved by the projected gradient descent method that can be painlessly plugged in normal fine-tuning. Extensive experiments and in-depth studies on diverse architectures/tasks like {BERT, RoBERTa, BART}, consistently endorse the superior parameter efficiency of AutoSparse to surpass state-of-the-arts. For instance, AutoSparse with BERT can operate at only 0.5% trainable parameters, while hitting an accuracy of 83.2<inline-formula><tex-math>$%$</tex-math></inline-formula> on MNLI-mismatched.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"18 6","pages":"1059-1069"},"PeriodicalIF":8.7,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"DDL: Empowering Delivery Drones With Large-Scale Urban Sensing Capability","authors":"Xuecheng Chen;Haoyang Wang;Yuhan Cheng;Haohao Fu;Yuxuan Liu;Fan Dang;Yunhao Liu;Jinqiang Cui;Xinlei Chen","doi":"10.1109/JSTSP.2024.3427371","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3427371","url":null,"abstract":"Delivery drones provide a promising sensing platform for smart cities thanks to their city-wide infrastructure and large-scale deployment. However, due to limited battery lifetime and available resources, it is challenging to schedule delivery drones to derive both high sensing and delivery performance, which is a highly complicated optimization problem with several coupled decision variables. Meanwhile, this complex optimization problem involves multiple interconnected decision variables, making it even more complex. In this paper, we first propose a delivery drone-based sensing system and formulate a mixed-integer non-linear programming problem (MINLP) that jointly optimizes the sensing utility and delivery time, considering practical factors including energy capacity and available delivery drones. Then we provide an efficient solution that integrates the strength of deep reinforcement learning (DRL) and heuristic, which decouples the highly complicated optimization search process and replaces the heavy computation with a rapid approximation. Evaluation results compared with the state-of-the-art baselines show that \u0000<italic>DDL</i>\u0000 improves the scheduling quality by at least 46% on average. More importantly, our proposed method could effectively improve the computational efficiency, which is up to 98 times higher than the best baseline.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"18 3","pages":"502-515"},"PeriodicalIF":8.7,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142137524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Plant-Physics-Guided Neural Network Control for Permanent Magnet Synchronous Motors","authors":"Zhenxiao Yin;Xu Chen;Yang Shen;Xiangdong Su;Dianxun Xiao;Dirk Abel;Hang Zhao","doi":"10.1109/JSTSP.2024.3430822","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3430822","url":null,"abstract":"In safety- and precision-critical control scenarios for permanent magnet synchronous motors (PMSMs), the external spontaneous disturbance causes unexpected speed drop. The disturbance occurs without routine, so it cannot be modeled specifically. The large speed drop and slow response speed cause a reduced life of the machines driven by PMSMs. Therefore, it is crucial to implement a method that can lead the controller to learn the effects caused by disturbances. To this end, this paper proposes a novel approach based on the basic structure of a backpropagation neural network (BP) for adaptive real-time adjustment in motor control. Regarding the lack of explainability of BP in existing methods, the electric motor physics is embedded into the BP (BP-PHY) gradient update part to enlarge the range of stability. To overcome the shortage of a potentially unstable output of neural network (NN), the learning parameter of NN is tailored based on the stability theory and motor physics. Finally, the proposed methods are implemented into simulations and experiments. The recovery time after disturbance decreases to 51.3% and the speed drop decreases to 50.3% compared to the basic controller of the PMSM, while the control stability of the NN is ensured.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 1","pages":"74-87"},"PeriodicalIF":8.7,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Federated Learning at Scale: Addressing Client Intermittency and Resource Constraints","authors":"Mónica Ribero;Haris Vikalo;Gustavo de Veciana","doi":"10.1109/JSTSP.2024.3430118","DOIUrl":"https://doi.org/10.1109/JSTSP.2024.3430118","url":null,"abstract":"In federated learning systems, a server coordinates the training of machine learning models on data distributed across a number of participating client devices. In each round of training, the server selects a subset of devices to perform model updates and, in turn, aggregates those updates before proceeding to the next round of training. Most state-of-the-art federated learning algorithms assume that the clients are always available to perform training – an assumption readily violated in many practical settings where client availability is intermittent or even transient; moreover, in systems where the server samples from an exceedingly large number of clients, a client will likely participate in at most one round of training. This can lead to biasing the learned global model towards client groups endowed with more resources. In this paper, we consider systems where the clients are naturally grouped based on their data distributions, and the groups exhibit variations in the number of available clients. We present <sc>Flics-opt</small>, an algorithm for large-scale federated learning over heterogeneous data distributions, time-varying client availability and further constraints on client participation reflecting, e.g., overall energy efficiency objectives that should be met to achieve sustainable deployment. In particular, <sc>Flics-opt</small> dynamically learns a selection policy that adapts to client availability patterns and communication constraints, ensuring per-group long-term participation which minimizes the variance inevitably introduced into the learning process by client sampling. We show that for non-convex smooth functions <sc>Flics-opt</small> coupled with SGD converges at <inline-formula><tex-math>$O(1/sqrt{T})$</tex-math></inline-formula> rate, matching the state-of-the-art convergence results which require clients to be always available. We test <sc>Flics-opt</small> on three realistic federated datasets and show that, in terms of maximum accuracy, <sc>Flics-Avg</small> and <sc>Flics-Adam</small> outperform traditional <sc>FedAvg</small> by up to 280% and 60%, respectively, while exhibiting robustness in face of heterogeneous data distributions.","PeriodicalId":13038,"journal":{"name":"IEEE Journal of Selected Topics in Signal Processing","volume":"19 1","pages":"60-73"},"PeriodicalIF":8.7,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}