检索结果-内蒙古大学图书馆

Enabling Communication-Efficient Federated Learning via Distributed Compressed Sensing

学校读者我要写书评

暂无评论

Enabling Communication-Efficient Federated Learning via Dist...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yixuan Guan Xuefeng Liu Tao Ren Jianwei Niu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Laboratory for Internet Software Technologies Institute of Software Chinese Academy of Sciences Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

Federated learning (FL) trains a shared global model by periodically aggregating gradients from local devices. Communication overhead becomes a principal bottleneck in FL since participating devices usually suffer from limited bandwidth and unreliable connections in uplink transmission. To address this problem, the gradient compression methods based on compressed sensing (CS) theory have been put forward recently. However, most existing CS-based works compress gradients independently, ignoring the gradient correlations between participants or adjacent communication rounds, which constrains the achievement of higher compression rates. In view of the above observation, we propose a novel gradient compression scheme named FedDCS, guided by distributed compressed sensing (DCS) theory. Following the design philosophy of separate encoding and joint decoding in DCS, FedDCS compresses gradients for participants in each round separately while reconstructing them at the central server jointly via fully exploiting correlated gradients from the previous round, which are known as side information (SI). Benefiting from this design, reconstruction performance is significantly improved with fewer decoding errors also iterations under the identical compression rate, and the total uploading bits to achieve model convergence are considerably reduced. Theoretical analysis and extensive experiments conducted on MNIST and Fashion-MNIST both verify the effectiveness of our approach.

关键词：

A Phase Estimation Algorithm for Quantum Speed-Up Multi-Party Computing

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第4期67卷 241-252页

作者： Wenbin Yu Hao Feng Yinsong Xu Na Yin Yadang Chen Zhi-Xin Yang Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Jiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Department of Computer Science and Engineering Michigan State UniversityEast Lansing48824MIUSA State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering University of Macao999078Macao

Security and privacy issues have attracted the attention of researchers in the field of IoT as the information processing scale grows in sensor *** computing,theoretically known as an absolutely secure way to store and transmit information as well as a speed-up way to accelerate local or distributed classical algorithms that are hard to solve with polynomial complexity in computation or *** this paper,we focus on the phase estimation method that is crucial to the realization of a general multi-party computing model,which is able to be accelerated by quantum algorithms.A novel multi-party phase estimation algorithm and the related quantum circuit are proposed by using a distributed Oracle operator with *** proved theoretical communication complexity of this algorithm shows it can give the phase estimation before applying multi-party computing efficiently without increasing any additional ***,a practical problem of multi-party dating investigated shows it can make a successful estimation of the number of solution in advance with zero communication complexity by utilizing its special statistic *** simulations present the correctness,validity and efficiency of the proposed estimation method.

关键词： Edge computing security multi-party computing quantum algorithm phase estimation communication complexity

TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Shaoqing Li, Fang Huang, Peixiang Song, Ziying Yang, Zhi-Xin State Key Laboratory of Internet of Things for Smart City Department of Electromechanical Engineering University of Macau 999078 China School of Mechanical Engineering Beijing Institute of Technology China College of Engineering Peking University Beijing China School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China

Accurate multi-view 3D object detection is essential for applications such as autonomous driving. Researchers have consistently aimed to leverage LiDAR’s precise spatial information to enhance camera-based detectors through methods like depth supervision and bird-eye-view (BEV) feature distillation. However, existing approaches often face challenges due to the inherent differences between LiDAR and camera data representations. In this paper, we introduce the TiGDistill-BEV, a novel approach that effectively bridges this gap by leveraging the strengths of both sensors. Our method distills knowledge from diverse modalities(e.g., LiDAR) as the teacher model to a camera-based student detector, utilizing the Target Inner-Geometry learning scheme to enhance camera-based BEV detectors through both depth and BEV features by leveraging diverse modalities. Specially, we propose two key modules: an inner-depth supervision module to learn the low-level relative depth relations within objects which equips detectors with a deeper understanding of object-level spatial structures, and an inner-feature BEV distillation module to transfer high-level semantics of different keypoints within foreground targets. To further alleviate the domain gap, we incorporate both inter-channel and inter-keypoint distillation to model feature similarity. Extensive experiments on the nuScenes benchmark demonstrate that TiGDistill-BEV significantly boosts camera-based only detectors achieving a state-of-the-art with 62.8% NDS and surpassing previous methods by a significant margin. The codes is available at: https://***/Public-BOTs/*** Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

A Contrastive Learning Based Unsupervised Multi-View Stereo with Multi-Stage Self-Training Strategy

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Wang, Zihang Luo, Haonan Wang, Xiang Zheng, Jin Ning, Xin Bai, Xiao School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University Beijing100191 China School of Computer and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China

Recent years, unsupervised multi-view stereo methods have achieved excellent success that can produce comparable results to earlier supervised ***, as unsupervised MVS uses image reconstruction as pretext task, it faces two vital drawbacks: RGB value, which is the the measurement of image, is not robust enough across views due to complicated environment like lighting conditions and reconstruction itself cannot reflect quality of depth estimation *** problems cause the actual optimization goal to diverge from the expected optimization goal, thus could impair the training *** enhance robustness of pretext task, we propose a contrastive learning based *** constraint adds featuremetric consistency across views by forcing the features between matching points similar and the features between unmatched points *** add linear properties to overall training procedure, we propose a multi-stage training strategy that uses pseudo label as supervision after unsupervised training at the *** the other hand, we adopt an iterative optimizer that proven to be quite effective in supervised MVS to accelerate ***, we conduct a series of experiments on the DTU dataset and Tanks and Temples dataset that demonstrate the efficiency and robustness of our method compared with the state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Image reconstruction

DLUE: Benchmarking Document Language Understanding

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Ruoxi Lin, Hongyu Guan, Xinyan Han, Xianpei Sun, Yingfei Sun, Le Chinese Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China

Understanding documents is central to many real-world tasks but remains a challenging topic. Unfortunately, there is no well-established consensus on how to comprehensively evaluate document understanding abilities, which significantly hinders the fair comparison and measuring the progress of the field. To benchmark document understanding researches, this paper summarizes four representative abilities, i.e., document classification, document structural analysis, document information extraction, and document transcription. Under the new evaluation framework, we propose Document Language Understanding Evaluation – DLUE, a new task suite which covers a wide-range of tasks in various forms, domains and document genres. We also systematically evaluate six well-established transformer models on DLUE, and find that due to the lengthy content, complicated underlying structure and dispersed knowledge, document understanding is still far from being solved, and currently there is no neural architecture that dominates all tasks, raising requirements for a universal document understanding architecture. © 2023, CC BY.

关键词： Information retrieval systems

Attribute-Specific Manipulation Based on Layer-Wise Channels

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yan, Yuanjie Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Electronic Science and Engineering Nanjing University Nanjing China School of Artificial Intelligence Nanjing University Nanjing China

Image manipulation on the latent space of the pre-trained StyleGAN can control the semantic attributes of the generated images. Recently, some studies have focused on detecting channels with specific properties to directly manipulate the latent code, which is limited by the entanglement of the latent space. To detect the attribute-specific channels, we propose a novel detection method in the context of pre-trained classifiers. We analyse the gradients layer by layer on the style space. The intensities of the gradients indicate the channel’s responses to specific attributes. The latent style codes of channels control separate attributes in the layers. We choose channels with the top-k gradients to control specific attributes in the maximum response layer. We implement single-channel and multi-channel manipulations with a certain attribute. Our methods can accurately detect relevant channels for a large number of face attributes. Extensive qualitative and quantitative results demonstrate that the proposed methods outperform state-of-the-art methods in generalization and scalability. © 2023, CC BY.

关键词： Semantics

Flat U-Net: An Efficient Ultralightweight Model for Solar Filament Segmentation in Full-disk Hα Images

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhu, GaoFei Lin, GangHua Yang, Xiao Zeng, Cheng School of Computer and Software Engineering Xihua University Chengdu610039 China National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China State Key Laboratory of Solar Activity and Space Weather National Space Science Center Chinese Academy of Sciences Beijing100190 China

Solar filaments are one of the most prominent features observed on the Sun, and their evolutions are closely related to various solar activities, such as flares and coronal mass ejections. Real-time automated identification of solar filaments is the most effective approach to managing large volumes of data. Existing models of filament identification are characterized by large parameter sizes and high computational costs, which limit their future applications in highly integrated and intelligent ground-based and space-borne observation devices. Consequently, the design of more lightweight models will facilitate the advancement of intelligent observation equipment. In this study, we introduce Flat U-Net, a novel and highly efficient ultralightweight model that incorporates simplified channel attention (SCA) and channel self-attention (CSA) convolutional blocks for the segmentation of solar filaments in full-disk Hα images. Feature information from each network layer is fully extracted to reconstruct interchannel feature representations. Each block effectively optimizes the channel features from the previous layer, significantly reducing parameters. The network architecture presents an elegant flattening, improving its efficiency, and simplifying the overall design. Experimental validation demonstrates that a model composed of pure SCAs achieves a precision of approximately 0.93, with dice similarity coefficient (DSC) and recall rates of 0.76 and 0.64, respectively, significantly outperforming the classical U-Net. Introducing a certain number of CSA blocks improves the DSC and recall rates to 0.82 and 0.74, respectively, which demonstrates a pronounced advantage, particularly concerning model weight size and detection effectiveness. The data set, models, and code are available as open-source resources. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

Accelerating MUS enumeration by inconsistency graph partitioning

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2019年第11期62卷 70-80页

作者： Jie LUO Shaofan LIU State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang University

The problem of finding minimal unsatisfiable subsets(MUSes) has been studied frequently because of its theoretical importance and wide range of applications in domains such as electronic design automation, software, and integrated circuit verification. In this paper, a method for accelerating the enumeration of MUSes based on inconsistency graph partitioning is proposed. First, an inconsistency graph of a set of clauses is constructed by extracting the inconsistency relations between literals of different clauses. In this paper, we show that by partitioning the inconsistency graph into small connected components through a vertex cut, the enumeration of MUSes in different components becomes independent and it is possible to compute them separately. Moreover, the MUSes of the original clause set can be constructed by merging the unit clauses in the MUSes of these connected components back into the clauses in the vertex cut. Experiments show that by integrating the acceleration method into the MARCO MUSes enumerator, there is a 2–3 times improvement in the average runtime of solved instances for randomly generated benchmarks. By integrating the acceleration method into itself as an MUS enumerator, there is another 3–4 times improvement when compared with the accelerated MARCO.

关键词： minimal unsatisfiable subsets inconsistency graph graph partition SAT UNSAT

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

学校读者我要写书评

暂无评论

Detecting Backdoors During the Inference Stage Based on Corr...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Xiaogeng Liu Minghui Li Haoyu Wang Shengshan Hu Dengpan Ye Hai Jin Libing Wu Chaowei Xiao School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Software Engineering Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan University School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab Arizona State University

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo) 1 1 https://***/CGCL-codes/TeCo, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability.

关键词：