检索结果-内蒙古大学图书馆

Re-quantization based binary graph neural networks

science China(Information sciences) 2024年第7期67卷 160-171页

作者： Kai-Lang YAO Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing University

Binary neural networks have become a promising research topic due to their advantages of fast inference speed and low energy consumption. However, most existing studies focus on binary convolutional neural networks, while less attention has been paid to binary graph neural networks. A common drawback of existing studies on binary graph neural networks is that they still include lots of inefficient full-precision operations in multiplying three matrices and are therefore not efficient enough. In this paper, we propose a novel method, called re-quantization-based binary graph neural networks(RQBGN), for binarizing graph neural networks. Specifically, re-quantization, a necessary procedure contributing to the further reduction of superfluous inefficient full-precision operations, quantizes the results of multiplication between any two matrices during the process of multiplying three matrices. To address the challenges introduced by requantization, in RQBGN we first study the impact of different computation orders to find an effective one and then introduce a mixture of experts to increase the model capacity. Experiments on five benchmark datasets show that performing re-quantization in different computation orders significantly impacts the performance of binary graph neural network models, and RQBGN can outperform other baselines to achieve state-of-the-art performance.

关键词： graph neural networks binary neural networks mixture of experts computation-efficient algorithms

来源：评论

学校读者我要写书评

暂无评论

Stochastic normalized gradient descent with momentum for large-batch training

引用

science China(Information sciences) 2024年第11期67卷 77-91页

作者： Shen-Yi ZHAO Chang-Wei SHI Yin-Peng XIE Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing University

Stochastic gradient descent(SGD) and its variants have been the dominating optimization methods in machine learning. Compared with SGD with small-batch training, SGD with large-batch training can better utilize the computational power of current multi-core systems such as graphics processing units(GPUs)and can reduce the number of communication rounds in distributed training settings. Thus, SGD with large-batch training has attracted considerable attention. However, existing empirical results showed that large-batch training typically leads to a drop in generalization accuracy. Hence, how to guarantee the generalization ability in large-batch training becomes a challenging task. In this paper, we propose a simple yet effective method, called stochastic normalized gradient descent with momentum(SNGM), for large-batch training. We prove that with the same number of gradient computations, SNGM can adopt a larger batch size than momentum SGD(MSGD), which is one of the most widely used variants of SGD, to converge to an?-stationary point. Empirical results on deep learning verify that when adopting the same large batch size,SNGM can achieve better test accuracy than MSGD and other state-of-the-art large-batch training methods.

关键词： non-convex problems large-batch training stochastic normalized gradient descent momentum

来源：评论

学校读者我要写书评

暂无评论

AsyCo: an asymmetric dual-task co-training model for partial-label learning

引用

science China(Information sciences) 2025年第5期68卷 332-347页

作者： Beibei LI Yiyuan ZHENG Beihong JIN Tao XIANG Haobo WANG Lei FENG College of Computer Science Chongqing University State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences School of Software Technology Zhejiang University School of Computer Science and Engineering Nanyang Technological University

Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error accumulation problems caused by mistakenly disambiguated instances. Although co-training can alleviate this issue by training two networks simultaneously and allowing them to interact with each other, most existing co-training methods train two structurally identical networks with the same task, i.e., are symmetric, rendering it insufficient for them to correct each other due to their similar limitations. Therefore, in this paper, we propose an asymmetric dual-task co-training PLL model called AsyCo,which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly by optimizing distinct tasks. Specifically, the disambiguation network is trained with a self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence. Finally, the error accumulation problem is mitigated via information distillation and confidence refinement. Extensive experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.

关键词： machine learning weakly supervised learning partial-label learning co-training models candidate label sets

来源：评论

学校读者我要写书评

暂无评论

Committed-programming reductions: formalizations,implications and relations

引用

science China(Information sciences) 2024年第10期67卷 151-171页

作者： Jiang ZHANG Yu YU Dengguo FENG Shuqin FAN Zhenfeng ZHANG State Key Laboratory of Cryptology Department of Computer Science and Engineering Shanghai Jiao Tong University Trusted Computing and Information Assurance Laboratory Institute of SoftwareChinese Academy of Sciences

In this work, we introduce a class of black-box(BB) reductions called committed-programming reduction(CPRed) in the random oracle model(ROM) and obtain the following interesting results:(1) we demonstrate that some well-known schemes, including the full-domain hash(FDH) signature(Eurocrypt1996) and the Boneh-Franklin identity-based encryption(IBE) scheme(Crypto 2001), are provably secure under CPReds;(2) we prove that a CPRed associated with an instance-extraction algorithm implies a reduction in the quantum ROM(QROM). This unifies several recent results, including the security of the Gentry-Peikert-Vaikuntanathan IBE scheme by Zhandry(Crypto 2012) and the key encapsulation mechanism(KEM) variants using the Fujisaki-Okamoto transform by Jiang et al.(Crypto 2018) in the ***, we show that CPReds are incomparable to non-programming reductions(NPReds) and randomly-programming reductions(RPReds) formalized by Fischlin et al.(Asiacrypt 2010).

关键词： provable security random oracle model quantum random oracle model black-box reduction/separation programmability

来源：评论

学校读者我要写书评

暂无评论

Enhanced Privacy-Preserving WiFi Fingerprint Localization from CL Encryption

引用

Chinese Journal of Electronics 2024年第6期33卷 1435-1446页

作者： Zhiwei WANG Qiuchi ZHU Zhenqi ZHANG School of Computer Nanjing University of Posts and Telecommunications State Key Laboratory of Public Big Data Guizhou University Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu University of Information Engineering Key Laboratory of Computational Science and Application of Hainan Province Hainan Normal University

The WiFi fingerprint-based localization method is considered one of the most popular techniques for indoor localization. In INFOCOM'14, Li et al. proposed a wireless fidelity(WiFi) fingerprint localization system based on Paillier encryption, which is claimed to protect both client C 's location privacy and service provider S's database privacy. However, Yang et al. presented a practical data privacy attack in INFOCOM'18, which allows a polynomial time attacker to obtain S's database. We propose a novel WiFi fingerprint localization system based on CastagnosLaguillaumie(CL) encryption, which has a trustless setup and is efficient due to the excellent properties of CL encryption. To prevent Yang et al.'s attack, the system requires that S selects only the locations from its database that can receive the nonzero signals from all the available access points in C 's nonzero fingerprint in order to determine C's location. Security analysis shows that our scheme is secure under Li et al.'s threat model. Furthermore, to enhance the security level of privacy-preserving WiFi fingerprint localization scheme based on CL encryption, we propose a secure and efficient zero-knowledge proof protocol for the discrete logarithm relations in C's encrypted localization queries.

关键词： Location awareness Threat modeling Data privacy Protocols Databases Fingerprint recognition Trustless services Encryption Servers Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learning

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-12页

作者： Zhang, Yanan Zhou, Chao Huang, Di State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China

Existing 3D object detection suffers from expensive annotation costs and poor transferability to unknown data due to the domain gap, Unsupervised Domain Adaptation (UDA) aims to generalize detection models trained in labeled source domains to perform robustly on unexplored target domains, providing a promising solution for cross-domain 3D object detection. Although Self-Training (ST) based cross-domain 3D detection methods with the assistance of pseudo-labeling techniques have achieved remarkable progress, they still face the issue of low-quality pseudo-labels when there are significant domain disparities due to the absence of a process for feature distribution alignment. While Adversarial Learning (AL) based methods can effectively align the feature distributions of the source and target domains, the inability to obtain labels in the target domain forces the adoption of asymmetric optimization losses, resulting in a challenging issue of source domain bias. To overcome these limitations, we propose a novel unsupervised domain adaptation framework for 3D object detection via collaborating ST and AL, dubbed as STAL3D, unleashing the complementary advantages of pseudo labels and feature distribution alignment. Additionally, a Background Suppression Adversarial Learning (BS-AL) module and a Scale Filtering Module (SFM) are designed tailored for 3D cross-domain scenes, effectively alleviating the issues of the large proportion of background interference and source domain size bias. Our STAL3D achieves state-of-the-art performance on multiple cross-domain tasks and even surpasses the Oracle results on Waymo $\rightarrow$ KITTI and Waymo $\rightarrow$ KITTI-rain. IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Heuristic Search with Cut Point Based Strategy for Critical Node Problem

引用

Journal of computer science & Technology 2024年第6期39卷 1328-1340页

作者： Zhi-Han Chen Shao-Wei Cai Jian Gao Shi-Ke Ge Chan-Juan Liu Jin-Kun Lin School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 101408China Key Laboratory of System Software(Chinese Academy of Sciences)and State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China College of Information Science and Technology Northeast Normal UniversityChangchun 130024China School of Computer Science and Technology Dalian University of TechnologyDalian 116024China SeedMath Technology Limited Beijing 100086China

The critical node problem(CNP)aims to deal with critical node identification in a graph,which has extensive applications in many *** CNP is a challenging task due to its computational complexity,and it attracts much attention from both academia and *** this paper,we propose a population-based heuristic search algorithm called CPHS(Cut Point Based Heuristic Search)to solve CNP,which integrates two main *** first one is a cut point based greedy strategy in the local search,and the second one involves the functions used to update the solution pool of the ***,a mutation strategy is applied to solutions with probability based on the overall average similarity to maintain the diversity of the solution *** are performed on a synthetic benchmark,a real-world benchmark,and a large-scale network benchmark to evaluate our *** with state-of-the-art algorithms,our algorithm has better performance in terms of both solution quality and run time on all the three benchmarks.

关键词： local search cut point heuristic search critical node problem

来源：评论

学校读者我要写书评

暂无评论

Will the fibers of the future be considered fibers?

引用

National science Review 2024年第10期11卷 15-17页

作者： Dewen Xu Ya Liu Hailiang Wang Wei Yan Changjun Jiang Meifang Zhu State Key Laboratory for Modification of Chemical Fibers and Polymer Materials College of Materials Science and Engineering Donghua University Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Department of Computer Science and Technology Tongji University

Fiber materials are key materials that have changed human history and promoted the progress of human civilization. In ancient times, humans used feathers and animal skins for clothing, and later they widely employed natural fibers such as cotton, hemp, silk and wool to make fabrics(Fig. 1a). Chinese ancestors had mastered the art of natural fiber weaving as early as the Neolithic *** thousand years ago, people were already familiar with and adept at techniques for spinning natural fibers [1].

关键词： future will considered fibers

来源：评论

学校读者我要写书评

暂无评论

Towards optimized tensor code generation for deep learning on sunway many-core processor

引用

Frontiers of computer science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

来源：评论

学校读者我要写书评

暂无评论

Understanding and Detecting Inefficient Image Displaying Issues in Android Apps

引用

Journal of computer science & Technology 2024年第2期39卷 434-459页

作者：李文杰马骏蒋炎岩许畅马晓星 State Key Laboratory of Novel Software Technology Nanjing UniversityNanjing 210023China Department of Computer Science and Technology Nanjing UniversityNanjing 210023China

Mobile applications(apps for short)often need to display ***,inefficient image displaying(IID)issues are pervasive in mobile apps,and can severely impact app performance and user *** paper first establishes a descriptive framework for the image displaying procedures of IID *** on the descriptive framework,we conduct an empirical study of 216 real-world IID issues collected from 243 popular open-source Android apps to validate the presence and severity of IID issues,and then shed light on these issues’characteristics to support research on effective issue *** the findings of this study,we propose a static IID issue detection tool TAPIR and evaluate it with 243 real-world Android ***,49 and 64 previously-unknown IID issues in two different versions of 16 apps reported by TAPIR are manually confirmed as true positives,respectively,and 16 previously-unknown IID issues reported by TAPIR have been confirmed by developers and 13 have been ***,we further evaluate the performance impact of these detected IID issues and the performance improvement if they are *** results demonstrate that the IID issues detected by TAPIR indeed cause significant performance degradation,which further show the effectiveness and efficiency of TAPIR.

关键词： Android application(app) inefficient image displaying(IID) performance empirical study static analysis

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：