检索结果-内蒙古大学图书馆

GAEM: Graph-driven Attention-based Entropy Model for LiDAR Point Cloud Compression

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Cui, Mingyue Zhong, Yuyang Feng, Mingjian Long, Junhua Ling, Yehua Xu, Jiahao Huang, Kai Sun Yat-sen University School of Computer Science and Engineering Guangzhou400100 China Sun Yat-sen University key Laboratory of Machine Intelligence and Advanced Computing Guangzhou400100 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Guangxi Transportation Science and Technology Group Co. Ltd Nanning530029 China

High-quality LiDAR point cloud (LPC) coding is essential for efficiently transmitting and storing the vast amounts of data required for accurate 3D environmental representation. The Octree-based entropy coding framework has emerged as the predominant method, however, previous study usually overly relies on large-scale attention-based context prediction to encode Octree nodes, overlooking the inherent correlational properties of this structure. In this paper, we propose a novel Graph-driven Attention-based Entropy Model (GAEM), which adopts partitioned graph attention mechanisms to uncover contextual dependencies among neighboring nodes. Different from the Cartesian coordinate-based coding mode with higher redundancy, GAEM uses the multi-level spherical Octree to organize point clouds, improving the quality of LPC reconstruction. GAEM combines graph convolution for node feature embedding and grouped-graph attention for exploiting dependency among contexts, which preserves performance in low-computation using localized nodes. Besides, to further increase the receptive field, we design a high-resolution cross-attention module introducing sibling nodes. Experimental results show that our method achieves state-of-the-art performance on the LiDAR benchmark SemanticKITTI and MPEG-specified dataset Ford, compared to all baselines. Compared to the benchmark GPCC, our method achieves gains of up to 53.9% and 53.6% on SemanticKITTI and Ford while compared to the sibling-introduced methods, we achieve up to 42.3% and 44.7% savings in encoding/decoding time. In particular, our GAEM allows for extension to downstream tasks (i.e., vehicle detection and semantic segmentation), further demonstrating the practicality of the method. (Figure presented) © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Contextual Caching for Mobile Edge Large Language Model Service

arXiv

引用

arXiv 2025年

作者： Liu, Guangyuan Liu, Yinqiu Wang, Jiacheng Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore

Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external knowledge bases, inefficient cache management can still result in high retrieval latency and frequent cache updates. To address these issues, we propose an Adaptive Contextual Caching (ACC) framework that anticipates user needs by proactively caching semantically relevant data for mobile-edge LLMs. ACC utilizes a deep reinforcement learning (DRL) module to refine cache replacement policies, balancing user context, document similarity, and the overhead associated with cache misses. Experimental results demonstrate that ACC increases cache hit rates to over 80% after only 11 training episodes, outperforming FIFO, LRU, and semantic-only caching while reducing retrieval latency by up to 40%. In particular, ACC also reduces local caching overhead (i.e., the cost of updating the cache when a miss occurs) by as much as 55%, enabling scalable, low-latency LLM services in resource-constrained edge environments. © 2025, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Reveal training performance mystery between Tensor Flow and PyTorch in the single GPU environment

引用

Science China(Information Sciences) 2022年第1期65卷 147-163页

作者： Hulin DAI Xuan PENG Xuanhua SHI Ligang HE Qian XIONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabSchool of Computer Science and Technology Huazhong University of Science and Technology Department of Computer Science University of Warwick

Deep learning has gained tremendous success in various fields while training deep neural networks(DNNs) is very compute-intensive, which results in numerous deep learning frameworks that aim to offer better usability and higher performance to deep learning practitioners. Tensor Flow and Py Torch are the two most popular frameworks. Tensor Flow is more promising within the industry context, while Py Torch is more appealing in academia. However, these two frameworks differ much owing to the opposite design philosophy:static vs dynamic computation graph. Tensor Flow is regarded as being more performance-friendly as it has more opportunities to perform optimizations with the full view of the computation graph. However, there are also claims that Py Torch is faster than Tensor Flow sometimes, which confuses the end-users on the choice between them. In this paper, we carry out the analytical and experimental analysis to unravel the mystery of comparison in training speed on single-GPU between Tensor Flow and Py Torch. To ensure that our investigation is as comprehensive as possible, we carefully select seven popular neural networks, which cover computer vision, speech recognition, and natural language processing(NLP). The contributions of this work are two-fold. First, we conduct the detailed benchmarking experiments on Tensor Flow and Py Torch and analyze the reasons for their performance difference. This work provides the guidance for the end-users to choose between these two frameworks. Second, we identify some key factors that affect the performance,which can direct the end-users to write their models more efficiently.

关键词： deep learning performance comparison TensorFlow PyTorch

来源：评论

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

Downstream-agnostic Adversarial Examples

引用

International Conference on Computer Vision (ICCV)

作者： Ziqi Zhou Shengshan Hu Ruizhi Zhao Qian Wang Leo Yu Zhang Junhui Hou Hai Jin 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 Cyber Science and Engineering Wuhan University School of Information and Communication Technology Griffith University Department of Computer Science City University of Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Feature Distribution Smoothing Network Based on Gaussian Distribution for QoS Prediction

A Feature Distribution Smoothing Network Based on Gaussian D...

引用

IEEE International Conference on Web Services (ICWS)

作者： Tongxin Lu Xiaohong Zhang Ziliang Wang Meng Yan Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) China School of Big Data and Software Engineering Chongqing University Chongqing China

With the increasing number of services and their homogenization, the use of Quality of Service (QoS) for recommendations has become necessary. However, existing QoS prediction solutions have limitations in solving the noise and label imbalance problems of dataset, which greatly limit the improvement of QoS prediction accuracy. In this paper, we propose FSNet that contains a feature distribution smoothing module and an improved W-Huber loss function. The feature distribution smoothing module mitigates the effect of noise problem by fitting potential Gaussian distribution of known features with a supervised feedforward neural network. W-Huber loss function mitigates the impact of label imbalance problem on QoS prediction by reweighting the two components of Huber loss function. We conduct extensive experiments on real large-scale QoS dataset, and the results demonstrate that the proposed FSNet method outperforms existing QoS prediction methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Block Broyden's methods for solving nonlinear equations 23

Block Broyden's methods for solving nonlinear equations

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Chengchang Liu Cheng Chen Luo Luo John C.S. Lui Department of Computer Science & Engineering The Chinese University of Hong Kong Shanghai Key Laboratory of Trustworthy Computing East China Normal University School of Data Science Fudan University

This paper studies quasi-Newton methods for solving nonlinear equations. We propose block variants of both good and bad Broyden's methods, which enjoy explicit local superlinear convergence rates. Our block good Broyden's method has a faster condition-number-free convergence rate than existing Broyden's methods because it takes the advantage of multiple rank modification on Jacobian estimator. On the other hand, our block bad Broyden's method directly estimates the inverse of the Jacobian provably, which reduces the computational cost of the iteration. Our theoretical results provide some new insights on why good Broyden's method outperforms bad Broyden's method in most of the cases. The empirical results also demonstrate the superiority of our methods and validate our theoretical analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ethereum Smart Contract Representation Learning for Robust Bytecode-Level Similarity Detection 34

Ethereum Smart Contract Representation Learning for Robust B...

引用

34th International Conference on Software engineering and Knowledge engineering, SEKE 2022

作者： Tian, Zhenzhou Huang, Yaqian Tian, Jie Wang, Zhongmin Chen, Yanping Chen, Lingwei School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an710121 China Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an710121 China Department of Computer Science and Engineering Wright State University DaytonOH United States

ISBN: (纸本)1891706543

Smart contracts are programs that run on a blockchain, where Ethereum is one of the most popular ones supporting them. Due to the fact that they are immutable, it is essential to design smart contracts bug-free before they are deployed. However, various defects have been found in the deployed smart contracts, causing huge economic losses and lowing people's trust. Writing secure smart contracts is far from trivial, where developers tend to engage in reliable resources or social coding platforms to reuse code. This leads to a large number of similar contracts with potential security risks. Therefore, detecting similarity of smart contracts helps to avoid vulnerabilities, identify threats, and improve the security of Ethereum. In this paper, we design a learning-effective and cost-efficient model, called SmartSD, for Ethereum smart contract similarity detection. Different from the current research efforts, SmartSD is performed on a bytecode level and leverages deep neural networks to learn the latent representations from the opcode sequences for smart contract bytecodes, where the representation learning and similarity measurement are supervised via siamese neural networks. The experimental evaluations demonstrate that SmartSD outperforms EClone's 93.27% accuracy, achieving 98.37% high detection accuracy and 0.9850 F1-score, which is computationally tractable and effectively mitigates the interference caused by compilers. © 2022 Knowledge Systems Institute Graduate school. All rights reserved.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

A multi-dimensional index for privacy-preserving queries in cloud computing

A multi-dimensional index for privacy-preserving queries in ...

引用

作者： Xu, Hui Ding, Xiaofeng Jin, Hai Yu, Qing 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 Wuhan China

Although cloud computing saves the cost of enterprises and individuals to manage data in various applications on public cloud servers, it also causes the problem of the leakage of critical personal information and sensitive data. Therefore, the issues about data privacy of the published personal information have become a challenging problem. Most of the existing methods focus on cryptography-based techniques by encrypting the sensitive data before publishing. However, these techniques are either too computation expensive or only some authorized users can get access to the encrypted cloud data. The consequence is that the search response time is not satisfactory and the sharing extent of the cloud data is becoming limited. Motivated by this, we propose a perturbation-based method to preserve the privacy of data in cloud. To accelerate the query processing without privacy breaches, a high-efficiency multi-dimensional index is built for answering range counting queries under differential privacy, which embeds privacy-preserving R-tree index in Content Addressable Network. Experimental results demonstrate that our methods not only protect data privacy in different degree, but also accelerate the query speed efficiently. Compared with the existing method Quad-opt, our method provides about 20% better data utility under the same differential privacy principles. © 2019 John Wiley & Sons, Ltd.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Vader protocol based sentiment analysis technique using LSTM for Stock Trend prediction 14

Vader protocol based sentiment analysis technique using LSTM...

引用

14th International Conference on computing Communication and Networking Technologies, ICCCNT 2023

作者： Ticku, Amrita Tripathy, Niva Mishra, Pankaj Kumar Sinha, Anurag Jadon, Shivangi Raj, Aditya Kulshrestha, Harsh Rai, Vipin Shamim, Rejuwan Bharti Vidyapeeth's College of Engineering India Driems Autonomous Engineering College Cuttack India Rungta College of Engg. & Technology R1 Department of Electronics and Telecommunication Engg. CG Bhilai India Ignou School of Computing and Information Science New Delhi India Galgotias University Dept. of Computer Science and Engineering Noida India Galgotias University Department of Computer Science and Engineering Noida India Maharishi University of Information Technology Dept. of Computer Science and Engineering with Data Science Noida India

ISBN: (纸本)9798350335095

Stock prediction has always been a difficult task, and numerous strategies for predicting stock market behavior have been offered. Researchers have recently begun to investigate the use of sentimental analysis and deep learning models such as Long Short-Term Memory (LSTM) to predict stock prices. We offer a stock prediction model that integrates sentimental analysis and LSTM in this research. The model considers the mood of stock market news items and use LSTM to forecast future stock prices. The results of our suggested model's evaluation on the S& P 500 dataset reveal that it outperforms traditional stock prediction approaches. © 2023 IEEE.

关键词： Forecasting

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：