检索结果-内蒙古大学图书馆

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Wang, Jihe Wu, Ying Wang, Danghui School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798400706011

Training big graph neural networks (GNNs) in distributed systems is quite time-consuming mainly because of the ubiquitous aggregate operations that involve a large amount of cross-partition communication for collecting embeddings/gradients during the forward and backward propagation. To reduce the volume of the communication, some recent approaches focused on decaying each of connections via sampling, quantifying, or delaying until satisfactory trade-off are obtained between volume and accuracy. However, when applied to popular GNNs, those approaches are found to be bounded by a common volume/accuracy Pareto frontier which shows that the decaying for individual connection cannot further accelerate the aggregate of training. In this work, SC-GNN, a semantic compression of the cross-partition communication, is proposed to concentrate a group of connections as a high-level semantics and transmit to a target partition. Since carrying the overall intent of a group, the semantics can keep transferring the interactions, i.e., embeddings/gradients, between a pair of remote partitions until GNN models converge. In addition, a connection-pattern based differential optimization is proposed to further prune those weak connections, while guaranteeing the training accuracy. The results show that, for multi-field datasets, the compression rate of SC-GNN is 40.8 × higher than SOTA methods and the epoch time is reduced to 31.8% on average. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Repeat Request Design in AoI-Aware Broadcast With Heterogeneous Direct and Relay-Assisted Users

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Xueer Pan, Haoyuan Chan, Tse-Tin Li, Jianqiang Shenzhen University College of Computer Science and Software Engineering Shenzhen China The Education University of Hong Kong Department of Mathematics and Information Technology Hong Kong Shenzhen University National Engineering Laboratory for Big Data System Computing Technology The College of Computer Science and Software Engineering Shenzhen China

This paper investigates the design of automatic repeat request (ARQ) protocols in age of information (AoI)-aware broadcast systems with heterogeneous users, including both direct and relay-assisted users. In this setup, a direct user receives status updates directly via a single-hop link, while a relay-assisted user can receive status updates through either a direct single-hop link or a two-hop relay-assisted link. While ARQ is commonly used to ensure reliable transmission in error-prone wireless networks, previous studies suggest that ARQ does not improve the average AoI in single-hop networks. However, its impact on AoI in systems with relays, particularly those involving heterogeneous users, remains unclear. We address this gap by analyzing the average AoI under different ARQ strategies, introducing a transmission limit k ≥ 0 at the relay. Here, k = 0, k = 1, and k > 1 correspond to non-relay, non-ARQ-at-relay, and truncated-ARQ-at-relay strategies, respectively. Utilizing a unified Markov chain framework that models the transmission processes for each user type, we derive the theoretical average AoI. Our results show that the direct user benefits most from non-relay and non-ARQ strategies, similar to single-hop systems. In contrast, the relay-assisted user achieves optimal performance with truncated-ARQ-at-relay, leveraging both direct and relay-assisted links. For the overall system, applying a non-ARQ-at-relay approach strikes a balance in AoI between the direct and relay-assisted users, leading to a more stable and lower system-wide average AoI. © 2014 IEEE.

关键词： Mobile telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

Gradient Boosting-Accelerated Evolution for Multiple-Fault Diagnosis

Gradient Boosting-Accelerated Evolution for Multiple-Fault D...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Hongfei Wang Chenliang Luo Deqing Zou Hai Jin Wenjie Cai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Wuhan China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Wuhan China Huazhong University of Science and Technology Wuhan China Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan China College of Public Administration Wuhan China

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

Logic diagnosis is a key step in yield learning. Multiple faults diagnosis is challenging because of several reasons, including error masking, fault reinforcement, and huge search space for possible fault combinations. This work proposes a two-phase method for multiple-fault diagnosis. The first phase efficiently reduces the potential number of fault candidates through machine learning. The second phase obtains the final diagnosis results, by formulating the task as an combinational optimization problem that is later iteratively solved using binary evolution computation. Experiments shows that our method outperforms two existing methods for multiple-fault diagnosis, and achieves better diagnosability (improved by $1.87\times$ ) and resolution (improved by $1.42\times$ ) compared with a state-of-the-art commercial diagnosis tool.

关键词： Fault diagnosis Adaptation models Computational modeling Fitting Filtering algorithms Boosting Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

KubeSPT: Stateful Pod Teleportation for Service Resilience with Live Migration

引用

IEEE Transactions on Services computing 2025年

作者： Zhang, Hansheng Wu, Song Fan, Hao Huang, Zhuo Xue, Weibin Yu, Chen Ibrahim, Shadi Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong China

Container orchestration systems, such as Kubernetes, streamline containerized application deployment. As more and more applications are being deployed in Kubernetes, there is an increasing need for rescheduling - relocating a running pod to different nodes - due to system upgrades, node failures, and load-balancing optimizations. Live migration, which transfers services from source nodes to target nodes with minimal downtime, is the ideal support for rescheduling. However, implementing live migration for pods that run stateful services is challenging, because Kubernetes manages pods as stateless. First, the current pod's network namespace initialization process causes a mismatch in the network state between the migrated pod and internal containers. Second, migrating the memory state results in extended downtime. Third, Kubernetes operations on pods do not consider preserving the state of the pods. Therefore, we propose KubeSPT to achieve live migration of stateful pods in rescheduling scenarios. Firstly, we synchronize the network state of pods and internal containers by controlling packet flow and implement fast service redirection. Secondly, we introduce a Hot data and Lazy-Restore method for memory restoration to reduce migration downtime. Finally, we decouple pod migration operations from other Kubernetes operations to ensure compatibility with live migration. Experimental results show that KubeSPT reduces downtime by 86%-93% compared to current rescheduling methods. © 2008-2012 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

FedEAT: A Robustness Optimization Framework for Federated LLMs

arXiv

引用

arXiv 2025年

作者： Pang, Yahao Wu, Xingyuan Zhang, Xiaojin Chen, Wei Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Huazhong University of Science and Technology Wuhan China

Significant advancements have been made by Large Language Models (LLMs) in the domains of natural language understanding and automated content creation. However, they still face persistent problems, including substantial computational costs and inadequate availability of training data. The combination of Federated Learning (FL) and LLMs (federated LLMs) offers a solution by leveraging distributed data while protecting privacy, which positions it as an ideal choice for sensitive domains. However, Federated LLMs still suffer from robustness challenges, including data heterogeneity, malicious clients, and adversarial attacks, which greatly hinder their applications. We first introduce the robustness problems in federated LLMs, to address these challenges, we propose FedEAT (Federated Embedding space Adversarial Training), a novel framework that applies adversarial training in the embedding space of client LLM and employs a robust aggregation approach, specifically geometric median aggregation, to enhance the robustness of Federated LLMs. Our experiments demonstrate that FedEAT effectively improves the robustness of Federated LLMs with minimal performance loss. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Towards Demystifying Android Adware: dataset and Payload Location 39

Towards Demystifying Android Adware: Dataset and Payload Loc...

引用

39th ACM/IEEE International Conference on Automated Software engineering Workshops, ASEW 2024

作者： Wang, Chao Liu, Tianming Zhao, Yanjie Zhang, Lin Du, Xiaoning Li, Li Wang, Haoyu Monash University Clayton Australia Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security China The National Computer Emergency Response Beijing China Beihang University Beijing China

ISBN: (纸本)9798400712494

Adware represents a pervasive threat in the mobile ecosystem, yet its inherent characteristics have been largely overlooked by previous research. This work takes a crucial step towards demystifying Android adware. We present a comprehensive, well-annotated Android adware dataset AdwareZoo, which comprises 15,996 adware samples across 118 distinct adware families collected from both security reports and app repositories, providing a robust foundation for in-depth analysis and future research. We identify adware family payloads by isolating packages from adware samples for VirusTotal rescanning. Our analysis unveils critical insights into the adware ecosystem, highlighting distinctive patterns in family naming conventions and exposing the unexpected classification of widely-used ad networks as adware. We identify diverse payload location strategies, with a notable finding that over 30% of adware families employ payloads beyond conventional Java/Kotlin code. Furthermore, we reveal several evasion techniques utilized by ad-ware, including package name obfuscation and dynamic payload loading. This research not only offers a robust foundation for understanding and combating adware but also highlights the pressing need for increased scrutiny of mobile advertising practices. © 2024 ACM.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Joint Sparsification and Quantization for Wireless Federated Learning under Communication Constraints 24

Joint Sparsification and Quantization for Wireless Federated...

引用

24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023

作者： Su, Junshen Wang, Xijun Chen, Xiang Cheng, Ray-Guang Sun Yat-Sen University School of Electronics and Information Technology Guangzhou China The Chinese University of HongKong Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen China National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei Taiwan

ISBN: (纸本)9781665496261

Communication efficiency is one of the key bottlenecks in Federated Learning (FL). Compression techniques, such as sparsification and quantization, are used to reduce communication overhead. However, joint designs of these techniques under communication constraints are not well-explored. This paper investigates the joint uplink compression problem in communication-constrained FL systems. We propose a Block-TopK sparsification scheme to reduce the proportion of bits used for locating entries of a sparsified vector. Considering the communication constraints, an optimization formulation is proposed to minimize the compression error. By solving the optimization problem, our joint compression method provides a better trade-off between sparsity budget and bit width. Numerical results demonstrate that our approach achieves 99.96% of baseline accuracy with only 1.56% of the baseline communication overhead when training ResNet-18 on CIFAR-10. © 2023 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge datacenters

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable computing 2025年

作者： Pei, Qiangyu Yuan, Yongjie Hu, Haichuan Wang, Lin Zhang, Dong Yan, Bingheng Yu, Chen Liu, Fangming Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology 1037 Luoyu Road Wuhan430074 China Paderborn University TU Darmstadt Germany Jinan Inspur Data Co. Ltd. China Huazhong University of Science and Technology Peng Cheng Laboratory China

The proliferation of deep-learning-based mobile and IoT applications has driven the increasing deployment of edge datacenters equipped with domain-specific accelerators. The unprecedented computing power offered by these accelerators puts a heavy burden on the cooling system, motivating more potent cooling techniques like cold water cooling. However, we observe that cold water cooling results in significant energy waste in edge datacenters due to the fluctuating resource utilization both spatially and temporally. To tackle this issue, we propose the concept of "working smarter"by slowing down accelerators deliberately whenever possible and enabling warm water cooling during these times to achieve cooling efficiency. Based on this concept, we develop Hyco - a hybrid water cooling system tailored for edge datacenters running deep learning workloads. First, Hyco features a zone-based cooling architecture enabling dynamic switching between cold water and warm water cooling. Then, based on a lightweight latency estimation method, Hyco incorporates a learning-based scheduling scheme to determine "which"accelerator workers and "when"to slow down through an adaptive and intelligent power-latency trade-off for deep learning models. The simulation with real-world traces shows that Hyco reduces the cooling energy consumption by up to 34.74× while satisfying latency constraints more than 99% of the time for deep-learning-based applications. © 2016 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PointFaceFormer: Local and Global Attention Based Transformer for 3D Point Cloud Face Recognition

PointFaceFormer: Local and Global Attention Based Transforme...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Ziqi Gao Qiufu Li Gui Wang Linlin Shen Computer Vision Institute Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science University of Nottingham Ningbo China

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Existing 3D point cloud-based facial recognition struggles to fully leverage both global and local information inherent in the 3D point cloud data. In this paper, we introduce the PointFaceFormer, the first Transformer model designed for 3D point cloud face recognition. It incorporates an attention mechanism based on dot product and cosine functions to construct a similarity Transformer architecture, which effectively extracts both local and global features from the point cloud data. Experimental results demonstrate that PointFaceFormer achieves a recognition accuracy of 89.08% and a verification accuracy of 76.93% on the large-scale facial point cloud dataset Lock3DFace, which is a new state-of-the-art in 3D face recognition. Furthermore, PointFaceFormer exhibits excellent generalization performance on cross-quality datasets. Additionally, we validate the effectiveness of the attention mechanism through ablation experiments, which justify the effectiveness of the proposed modules.

关键词： Point cloud compression Solid modeling Three-dimensional displays Attention mechanisms Accuracy Face recognition Transformers

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：