检索结果-内蒙古大学图书馆

Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Xi Li, Qin Cai, Haibin Wang, Ting MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China

Federated Learning (FL) empowers multiple clients to collaboratively train machine learning models without sharing local data, making it highly applicable in heterogeneous Internet of Things (IoT) environments. However, intrinsic heterogeneity in clients’ model architectures and computing capabilities often results in model accuracy loss and the intractable straggler problem, which significantly impairs training effectiveness. To tackle these challenges, this paper proposes a novel Heterogeneity-aware Personalized Federated Learning method, named HAPFL, via multi-level Reinforcement Learning (RL) mechanisms. HAPFL optimizes the training process by incorporating three strategic components: 1) An RL-based heterogeneous model allocation mechanism. The parameter server employs a Proximal Policy Optimization (PPO)-based RL agent to adaptively allocate appropriately sized, differentiated models to clients based on their performance, effectively mitigating performance disparities. 2) An RL-based training intensity adjustment scheme. The parameter server leverages another PPO-based RL agent to dynamically fine-tune the training intensity for each client to further enhance training efficiency and reduce straggling latency. 3) A knowledge distillation-based mutual learning mechanism. Each client deploys both a heterogeneous local model and a homogeneous lightweight model named LiteModel, where these models undergo mutual learning through knowledge distillation. This uniform LiteModel plays a pivotal role in aggregating and sharing global knowledge, significantly enhancing the effectiveness of personalized local training. Experimental results across multiple benchmark datasets demonstrate that HAPFL not only achieves high accuracy but also substantially reduces the overall training time by 20.9%-40.4% and decreases straggling latency by 19.0%-48.0% compared to existing solutions. © 2025, CC BY.

关键词： Federated learning

Prophet: SSD Failure Analysis and Prediction Guided by Flash Reliability Characteristics in Data centers

学校读者我要写书评

暂无评论

IEEE Transactions on computers 2025年

作者： Song, Yunpeng Liang, Yujiong Liu, Jialin Shi, Liang East China Normal University MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application Shanghai China East China Normal University School of Computer Science and Technology Shanghai China Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Wuhan China

Solid-state drives (SSDs) are massively deployed in various fields, especially in data centers, for their excellent cost-effectiveness. However, SSDs may fail due to their imperfect manufacturing processes, resulting in system-level failures and even downtime in data centers. This makes SSD failure prediction critical. Current studies focus on dealing with data missing, numerical normalization, and other statistical issues in using machine learning methods, but the consideration of the reliability characteristics of the underlying flash media of SSDs and the timeliness (time duration between predicted failure and real failure) of SSD failure prediction result is missing. In this work, we study the failure characteristics of over 200,000 drives from industry data centers over a 4-year period, as well as daily data. The relationship between SSD attribute values and failures is first investigated. Then, we analyzed the SSD failure characteristics from several aspects (causes, differences between failures, and timeliness of prediction results) relying on flash reliability characteristics. Based on these, a novel SSD failure prediction method (Prophet) is proposed. Specifically, Prophet contains the following two components. First, to cope with the differences between failures, a diff-state method is proposed for differential machine learning modeling of SSDs in different "States". We define the "State" of an SSD, which represents the range of values in which the SSD currently lies in terms of some key attributes. Through flash reliability characteristics, we distinguish between different failures before training the model to obtain accurate predictions of different failure behaviors. Second, a recovery period method is proposed to enhance the timeliness of SSD failure prediction result by designing the sample selection method. The enhanced timeliness can be utilized by operations personnel to handle failed SSDs, such as replacement and repair. The evaluation results of

关键词： Failure rate

A Robust and Generalized Gauss-Seidel Solver for Physically-correct Simultaneous collisions

学校读者我要写书评

暂无评论

Proceedings of the ACM on computer Graphics and Interactive Techniques 2025年第1期8卷 1-17页

作者： Huanbo Zhou Zhenyu Xu Xijun Liu Xinyu Zhang Software Engineering Institute East China Normal University Shanghai Shanghai China East China Normal University Shanghai Shanghai China Software Engineering Institute East China Normal University Shanghai Shanghai China Shanghai Key Laboratory of Trustworthy Computing Shanghai Shanghai China and Engineering Research Center of Software/Hardware Co-design Technology and Application MoE) Shanghai Shanghai China

Simulating multi-object collisions in real-time environments remains a significant challenge, particularly when handling simultaneous collisions in a physically accurate manner. Traditional Gauss-Seidel solvers, widely employed in physics engines, often fail to preserve the symmetry and consistency of multi-object interactions that are often observed in physics. In this paper, we present a generalized and robust Gauss-Seidel solver to overcome the difficulties in simultaneous collisions. Using spatial and temporal collision states to classify and resolve constraints, our algorithm ensures correct collision propagation and symmetry, addressing the limitations commonly found in existing solvers. Moreover, our algorithm can mitigate jitters caused by floating-point errors, ensuring smooth and stable collision responses. Our approach demonstrates fast convergence and improved accuracy in scenarios involving complex multi-object collisions.

关键词： Physically-based simulation Gauss-Seidel solver Simultaneous collisions

GIRP: Energy-Efficient QoS-Oriented Microservice Resource Provisioning via Multi-Objective Multi-Task Reinforcement Learning

学校读者我要写书评

暂无评论

IEEE Transactions on Mobile computing 2025年

作者： Yuan, Honggang Wang, Ting Fu, Min Shi, Yuanming East China Normal University MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Laboratory of Trustworthy Computing Shanghai200062 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore ShanghaiTech University School of Information Science and Technology Shanghai201210 China

Microservice architecture has revolutionized web service development by facilitating loosely coupled and independently developable components distributed as containers or virtual machines. While existing studies emphasize end-to-end latency, this paper investigates energy-efficient quality-of-service (QoS)-oriented microservice provisioning, focusing on both QoS satisfaction and power consumption (PC) conservation. We propose the Green and Intelligent Resource Provision (GIRP) architecture, integrating a data-driven energy-latency-aware resource allocation and scheduling manager to balance latency and PC. To reconcile the trade-offs involved, a dual-objective optimization problem is formulated to minimize latency and energy use by selecting proper servers, allocating CPU cores, and determining service replicas. To address challenges with discrete variables, dual objectives, and implicit mappings, we leverage a model-free deep deterministic policy gradient-based reinforcement learning algorithm. Specifically, we develop a multi-task agent via the Multi-gate Mixture-of-Experts model to simultaneously make two separate actions regarding CPU core numbers and service replica numbers, followed by a single-task agent to determine service scheduling. Extensive experiments on the DeathStarBenchmark testbed validate GIRP's effectiveness, demonstrating approximately 52% resource savings and a 43% reduction in PC compared to leading methods like Sinan, Firm, and heuristic-based algorithms. These results highlight GIRP's capability to optimize microservice orchestration by balancing end-to-end latency and power efficiency. © 2025 IEEE. All rights reserved.

关键词： Quality of service

New constructions of asymptotically optimal periodic and aperiodic quasi-complementary sequence sets

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Peng Heng, Ziling Li, Chengju School of Science Chang’an University Xi’an710064 China National Mobile Communications Research Laboratory Southeast University Nanjing211111 China MoE Engineering Research Center of Software/Hardware Co-design Technology and Application East China Normal University Shanghai200062 China

Quasi-complementary sequence sets (QCSSs) play an important role in multi-carrier code division multiple access (MC-CDMA) systems as they can support more users than perfect complementary sequence sets (PCSSs). The objective of this paper is to present new constructions of asymptotically optimal periodic and aperiodic QCSSs with large set sizes. Firstly, we construct a family of asymptotically optimal periodic (p2n, pn − 1, pn − 1, pn + 1) QCSSs with small alphabet size p, which has larger set size than the known family of periodic (pn(pn−1), pn−1, pn−1, pn+1) QCSSs. Secondly, we construct five new families of asymptotically optimal aperiodic QCSSs with large set sizes and low aperiodic tolerances. Each family of these aperiodic QCSSs has set size Θ(K2) for some flock size K. compared with known asymptotically optimal aperiodic QCSSs in the literature, the proposed aperiodic QCSSs by us have better parameters or new lengths of their constituent sequences. copyright © 2025, The Authors. All rights reserved.

关键词： code division multiple access

conZone: A Zoned Flash Storage Emulator for consumer Devices

学校读者我要写书评

暂无评论

ConZone: A Zoned Flash Storage Emulator for Consumer Devices

design, Automation and Test in Europe conference and Exhibition

作者： Dingcui Yu Jialin Liu Yumiao Zhao Wentong Li Ziang Huang Zonghuan Yan Mengyang Ma Liang Shi MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application East China Normal University Shanghai China College of Computer Science and Technology East China Normal University Shanghai China Software Engineering Institute East China Normal University Shanghai China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

considering the potential benefits to lifespan and performance, zoned flash storage is expected to be incorporated into the next generation of consumer devices. However, due to the limited volatile cache and heterogeneous flash cells of consumer-grade flash storage, adopting a zone abstraction requires additional internal hardware design to maximize its benefits. To understand and efficiently improve the hardware design on consumer-grade zoned flash storage, we present conZone—the first emulator tailored to the characteristics of consumer-grade zoned flash storage. Users can explore the internal architecture and management strategies of consumer-grade zoned flash storage and integrate the optimization with software. We validate the accuracy of conZone by realizing a hardware architecture for consumer-grade zoned flash storage and comparing it with the state-of-the-art. We also make a case study for read performance research with conZone to explore the design of mapping mechanisms and cache management strategies.

关键词： Performance evaluation Accuracy Europe computer architecture hardware software Planning Optimization Next generation networking

Archer: adaptive memory compression with page-association-rule awareness for high-speed response of mobile devices 25

学校读者我要写书评

暂无评论

Archer: adaptive memory compression with page-association-ru...

Proceedings of the 23rd USENIX conference on File and Storage Technologies

作者： Changlong Li Zongwei Zhu Chao Wang Fangming Liu Fei Xu Edwin H.-M. Sha Xuehai Zhou School of Computer Science and Technology East China Normal University and Jianghuai Advance Technology Center Hefei China and MoE Engineering Research Center of Hardware/Software Co-Design Technology and Application School of Software Engineering University of Science and Technology of China Hefei China and Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China Huazhong University of Science and Technology and Peng Cheng Laboratory School of Computer Science and Technology East China Normal University

ISBN: (纸本)9781939133458

In mobile systems, memory can be compressed page-by-page to save space. This approach is widely adopted because memory data is accessed by page. However, this paper shows that the system response speed is significantly limited by page-grained compression. In this paper, we observe that approximately a quarter of anonymous memory pages are highly correlated, even though the association is implicit. Inspired by this, we propose Archer, an association-rule-aware memory compression framework in mobile systems. Archer demonstrates that memory in mobile devices should be compressed using flexible granularity, rather than relying solely on traditional page compression. To further integrate associationrule mining techniques into system design, we redesign the LRU mechanism and propose an adaptive memory compression region. Experimental results show that the average app launching speed is 1.55x faster when enabling Archer, and the average photographic speed and frame rate increase by 1.42x and 1.31x, respectively, compared to the state-of-the-art.

关键词：

Satellite Federated Fine-Tuning for Foundation Models in Space computing Power Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhu, Yan Zhu, Jingyang Wang, Ting Shi, Yuanming Jiang, Chunxiao Letaief, Khaled Ben MoE Engineering Research-Center of Software/Hardware Co-design Technology and Application The Shanghai Key Lab. of Trustworthy Computing East China Normal University Shanghai200062 China School of Information Science and Technology ShanghaiTech University Shanghai201210 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Advancements in artificial intelligence (AI) and low-earth orbit (LEO) satellites have promoted the application of large remote sensing foundation models for various downstream tasks. However, direct downloading of these models for fine-tuning on the ground is impeded by privacy concerns and limited bandwidth. Satellite federated learning (FL) offers a solution by enabling model fine-tuning directly on-board satellites and aggregating model updates without data downloading. Nevertheless, for large foundation models, the computational capacity of satellites is insufficient to support effective on-board fine-tuning in traditional satellite FL frameworks. To address these challenges, we propose a satellite-ground collaborative federated fine-tuning framework. The key of the framework lies in how to reasonably decompose and allocate model components to alleviate insufficient on-board computation capabilities. During fine-tuning, satellites exchange intermediate results with ground stations or other satellites for forward propagation and back propagation, which brings communication challenges due to the special communication topology of space transmission networks, such as intermittent satellite-ground communication, short duration of satellite-ground communication windows, and unstable inter-orbit inter-satellite links (ISLs). To reduce transmission delays, we further introduce tailored communication strategies that integrate both communication and computing resources. Specifically, we propose a parallel intra-orbit communication strategy, a topology-aware satellite-ground communication strategy, and a latency-minimalization inter-orbit communication strategy to reduce space communication costs. Simulation results demonstrate significant reductions in training time with improvements of approximately 33%. copyright © 2025, The Authors. All rights reserved.

关键词： Satellite communication systems

SAFL: Structure-Aware Personalized Federated Learning via Client-Specific Clustering and SCSI-Guided Model Pruning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Nan Wang, Xiaolu Du, Xiao Cai, Puyu Wang, Ting Engineering Research Center of Software/Hardware Co-Design Technology and Application Ministry of Education the Shangh ai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China Software Engineering Institute East China Normal University Shanghai200050 China Computer Science Department New York University New YorkNY10012 United States

Federated Learning (FL) enables clients to collaboratively train machine learning models without sharing local data, preserving privacy in diverse environments. While traditional FL approaches preserve privacy, they often struggle with high computational and communication overhead. To address these issues, model pruning is introduced as a strategy to streamline computations. However, existing pruning methods, when applied solely based on local data, often produce sub-models that inadequately reflect clients’ specific tasks due to data insufficiency. To overcome these challenges, this paper introduces SAFL (Structure-Aware Federated Learning), a novel framework that enhances personalized federated learning through client-specific clustering and Similar Client Structure Information (SCSI)-guided model pruning. SAFL employs a two-stage process: initially, it groups clients based on data similarities and uses aggregated pruning criteria to guide the pruning process, facilitating the identification of optimal sub-models. Subsequently, clients train these pruned models and engage in server-based aggregation, ensuring tailored and efficient models for each client. This method significantly reduces computational overhead while improving inference accuracy. Extensive experiments demonstrate that SAFL markedly diminishes model size and improves performance, making it highly effective in federated environments characterized by heterogeneous data. copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning