检索结果-内蒙古大学图书馆

Exploring Communication-efficient Federated Learning via Stateless In-network Aggregation

IEEE Transactions on Mobile Computing 2025年

作者： Xia, Junxu Cheng, Geyao Wu, Wenfei Luo, Lailong Guo, Deke National University of Defense Technology National Key Laboratory of Information Systems Engineering Changsha Hunan410073 China National University of Defense Technology State Key Laboratory of Complex & Critical Software Environment College of Information and Communication Changsha Hunan410073 China Peking University School of Computer Science Beijing100091 China

As an ambitious training paradigm, federated learning has garnered increasing attention in recent years, which enables collaborative training of a global model without accessing users' private data. However, due to the simultaneous and constant model updates gathering from massive distributed clients, the central server generally becomes a performance bottleneck. Additionally, the stateful aggregation (retaining all the updates from each client) conducted by the central server further poses potential threats to privacy, since it may recover the raw data based on such model updates inversely. The state-of-the-art methodologies, however, fail to address these two problems concurrently and efficiently. To this end, we propose GAIN, a secure aggregation acceleration service for federated learning. At its core, GAIN leverages programmable switches deployed at the edge network to aggregate model updates in a stateless manner before transmitting them to the central server. Consequently, GAIN can accelerate the transmission and aggregation of model updates while eliminating the chance of recovering private data. We evaluate the performance of GAIN through FPGA-based experiments and large-scale simulations. The results show that GAIN can effectively reduce bandwidth overhead and achieve up to 4.11× training throughput acceleration while prioritizing privacy protection. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

TEMPO: Time-evolving multi-period observational anomaly detection method for space probes

引用

Chinese Journal of Aeronautics 2025年

作者： QIAO, Yiqun WANG, Tian LÜ, Jinhu LIU, Kexin School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Zhongguancun Laboratory Beijing100098 China State Key Laboratory of Complex & Critical Software Environment Beihang University Beijing100191 China

In space probes, anomaly detection of sequence data collected by various sensors is essential to help detect potential faults promptly, improve the reliability of equipment operation, and ensure the smooth operation of the mission. However, sensors’ signals often contain a superposition of various frequencies, changing fluctuations, and correlations between features. This complexity of data attributes makes building effective models challenging. This paper proposes a Time-Evolving Multi-Period Observational (TEMPO) anomaly detection method for space probes. First, fusing wavelet analysis and natural periods improves the ability to capture multi-period features in data. Then, the feature extraction framework proposed enhances the effectiveness of anomaly detection by comprehensively extracting the complex features of data through the multi-module synergy of temporal and channel. The results demonstrate that the proposed method enhances anomaly detection accuracy and its effectiveness is confirmed. Additionally, the ablation experiment results further validate the efficacy of each module. An evaluation of the algorithm's computational complexity confirms its suitability for real-time processing. © 2025 The Authors

关键词： Space probes

来源：评论

学校读者我要写书评

暂无评论

MAGIC: detecting advanced persistent threats via masked graph representation learning 24

MAGIC: detecting advanced persistent threats via masked grap...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Zian Jia Yun Xiong Yuhong Nan Yao Zhang Jinjing Zhao Mi Wen Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Software Engineering Sun Yat-sen University China National Key Laboratory of Science and Technology on Information System Security China Shanghai University of Electric Power China

ISBN: (纸本)9781939133441

Advance Persistent Threats (APTs), adopted by most delicate attackers, are becoming increasing common and pose great threat to various enterprises and institutions. Data provenance analysis on provenance graphs has emerged as a common approach in APT detection. However, previous works have exhibited several shortcomings: (1) requiring attack-containing data and a priori knowledge of APTs, (2) failing in extracting the rich contextual information buried within provenance graphs and (3) becoming impracticable due to their prohibitive computation overhead and memory *** this paper, we introduce MAGIC, a novel and flexible self-supervised APT detection approach capable of performing multi-granularity detection under different level of supervision. MAGIC leverages masked graph representation learning to model benign system entities and behaviors, performing efficient deep feature extraction and structure abstraction on provenance graphs. By ferreting out anomalous system behaviors via outlier detection methods, MAGIC is able to perform both system entity level and batched log level APT detection. MAGIC is specially designed to handle concept drift with a model adaption mechanism and successfully applies to universal conditions and detection scenarios. We evaluate MAGIC on three widely-used datasets, including both real-world and simulated attacks. Evaluation results indicate that MAGIC achieves promising detection results in all scenarios and shows enormous advantage over state-of-the-art APT detection approaches in performance overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

Distributed MPC Compensation-Based LFC for Heterogeneous Multi-area Interconnected Power systems 8th

Distributed MPC Compensation-Based LFC for Heterogeneous Mul...

引用

8th International Conference on Life system Modeling and Simulation, LSMS 2024 and 8th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2024

作者： Chi, Xiaobo Li, Xinyi Liu, Xiaolin Jia, Xinchun School of Automation and Software Engineering Shanxi University Taiyuan030031 China School of Mathematical Sciences Shanxi University Taiyuan030006 China The Key Laboratory of Complex Systems and Data Science Ministry of Education Taiyuan030006 China

ISBN: (纸本)9789819602247

This paper addresses the distributed load frequency control (LFC) problem for multi-area interconnected power systems (MAIPSs) with thermal and wind power generations, considering both inter-area and intra-area transmission delays and random packet losses induced by communication networks. Firstly, a heterogeneous framework of MAIPSs is constructed, where a networked distributed model predictive control (DMPC) scheme is proposed to compensate for transmission delays and random packet losses. Based on this framework, we then developed a distributed closed-loop LFC system model for heterogeneous MAIPS. Subsequently, a Luenberger observer is constructed to estimate the system state of the local area, and a networked feedback controller is designed to ensure stability with a certain H∞ performance level for the networked MAIPSs. Moreover, stability conditions and controller design criteria are provided by using the Lyapunov-Krasovskii stability theory. Finally, the control performance of the proposed method is verified through an example of a two-area interconnected power system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Breaking the SSL-AL Barrier: A Synergistic Semi-Supervised Active Learning Framework for 3D Object Detection

arXiv

引用

arXiv 2025年

作者： Wang, Zengran Zhang, Yanan Chen, Jiaxin Huang, Di State Key Laboratory of Complex and Critical Software Environment Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China

To address the annotation burden in LiDAR-based 3D object detection, active learning (AL) methods offer a promising solution. However, traditional active learning approaches solely rely on a small amount of labeled data to train an initial model for data selection, overlooking the potential of leveraging the abundance of unlabeled data. Recently, attempts to integrate semi-supervised learning (SSL) into AL with the goal of leveraging unlabeled data have faced challenges in effectively resolving the conflict between the two paradigms, resulting in less satisfactory performance. To tackle this conflict, we propose a Synergistic Semi-Supervised Active Learning framework, dubbed as S-SSAL. Specifically, from the perspective of SSL, we propose a Collaborative PseudoScene Pre-training (CPSP) method that effectively learns from unlabeled data without introducing adverse effects. From the perspective of AL, we design a Collaborative Active Learning (CAL) method, which complements the uncertainty and diversity methods by model cascading. This allows us to fully exploit the potential of the CPSP pre-trained model. Extensive experiments conducted on KITTI and Waymo demonstrate the effectiveness of our S-SSAL framework. Notably, on the KITTI dataset, utilizing only 2% labeled data, S-SSAL can achieve performance comparable to models trained on the full dataset. The code has been released at https://***/LandDreamer/S SSAL. Copyright © 2025, The Authors. All rights reserved.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

A digital image correlation method for strain measurement using higher-order X-ray optical field components

引用

Optics and Laser Technology 2025年 189卷

作者： Li, Zixin Su, Yong Li, Jia Yuan, Yajun Xiao, Yu Xu, Feng CAS Key Laboratory of Mechanical Behaviour and Design of Materials Department of Modern Mechanics CAS Center for Excellence in Complex System Mechanics University of Science and Technology of China Anhui Hefei230027 China School of Biomedical Engineering Anhui Medical University Hefei230032 China

To achieve highly sensitive characterization of internal material strain fields, this study proposes a digital image correlation strain field measurement method based on higher-order X-ray optical field *** method utilizes random gratings to modulate the X-ray optical field, extracts the information of higher-order field components during material deformation based on the discrepancy between the theoretical transmission model and the experimental measurement, and combines the extracted information with Digital Image Correlation (DIC) technology to achieve precise measurement of internal material strain *** to the experimental comparison and verification, the relative displacement difference between the deformation field distribution obtained by the proposed method and the results of the traditional absorption phase method in the non-boundary and stress concentration area proves that the correlation information of the higher order components can truly reflect the deformation characteristics of the ***, compared to traditional methods, this method demonstrates higher sensitivity in strain field characterization. Particularly in the measurement of shear strain at crack tips, its computational results align more closely with linear elastic fracture mechanics theoretical predictions, providing a novel experimental approach for studying material damage evolution and failure mechanisms. © 2025 Elsevier Ltd

关键词： Crack tips

来源：评论

学校读者我要写书评

暂无评论

Joint DNN Partition and Thread Allocation Optimization for Energy-Harvesting MEC systems

Joint DNN Partition and Thread Allocation Optimization for E...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Yizhou Shi Liying Li Yue Zeng Peijin Cong Junlong Zhou School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Mobile Communications Research Laboratory Southeast University Nanjing China Key Laboratory of Embedded System and Service Computing (Tongji University) Ministry of Education Shanghai China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Deep neural networks (DNNs) have demonstrated exceptional performance, leading to diverse applications across various mobile devices (MDs). Considering factors like portability and environmental sustainability, an increasing number of MDs are adopting energy harvesting (EH) techniques for power supply. However, the computational intensity of DNNs presents significant challenges for their deployment on these resource-constrained devices. Existing approaches often employ DNN partition or offloading to mitigate the time and energy consumption associated with running DNNs on MDs. Nonetheless, existing methods frequently fall short in accurately modeling the execution time of DNNs, and do not consider to use thread allocation for further latency and energy consumption optimization. To solve these problems, we propose a dynamic DNN partition and thread allocation method to optimize the latency and energy consumption of running DNNs on EH-enabled MDs. Specifically, we first investigate the relationship between DNN inference latency and allocated threads and establish an accurate DNN latency prediction model. Based on the prediction model, a DRL-based DNN partition (DDP) algorithm is designed to find the optimal partitions for DNNs. A thread allocation (TA) algorithm is proposed to reduce the inference latency. Experimental results from our test-bed platform demonstrate that compared to four benchmarking methods, our scheme can reduce DNN inference latency and energy consumption by up to 37.3% and 38.5%.

关键词： Energy consumption Instruction sets Heuristic algorithms Artificial neural networks Predictive models Prediction algorithms Inference algorithms Partitioning algorithms Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Correction: CMAE-3D: Contrastive Masked AutoEncoders for Self-Supervised 3D Object Detection(International Journal of Computer Vision, 10.1007/s11263-024-02313-2)

引用

International Journal of Computer Vision 2025年第6期133卷 3803-3803页

作者： Zhang, Yanan Chen, Jiaxin Huang, Di State Key Laboratory of Complex and Critical Software Environment Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Hangzhou Innovation Institute Beihang University Hangzhou310051 China

The original version of this article unfortunately contained error in co-author’s affiliation. The first affiliation should be State key laboratory of complex and Critical software Environment, Beihang University, Beijing 100191, China instead of State key laboratory of complex and Critical software Environment, School of Computer Science and engineering, Beihang University, Beijing 100191, China. Also, the author Yanan Zhang is affiliated with School of Computer Science and engineering, Beihang University, Beijing 100191, China. The original article has been corrected. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：