检索结果-内蒙古大学图书馆

Time Series Anomaly Detection Based on Normalized Flow and Bayesian Networks

学校读者我要写书评

暂无评论

Time Series Anomaly Detection Based on Normalized Flow and B...

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Honglei Yao Donglan Liu Yingxian Chang Xin Liu Chaofan Tang State Grid Shandong Electric Power Research Institute Jinan China State Grid Shandong Electric Power Company Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Time series anomaly detection often faces significant challenges due to the high dimensionality, interdependence, and label sparsity of the data. Traditional methods struggle to model the intricate relationships between multiple time series components and often fail to accurately detect anomalies due to insufficient data dependence mining. To address these issues, we introduce GCRNF, a novel Graph-Enhanced Standardized Flow Model that incorporates a Bayesian network for causality modeling. This model decomposes joint probabilities into conditional probabilities and utilizes a graph dependency encoder with hybrid CNN-RNN models and Graph Convolutional Networks (GCNs). Our experimental results demonstrate that GCRNF outperforms existing methods in density estimation, anomaly detection, and drift identification within time series distributions. Specifically, GCRNF showed a significant improvement in detection accuracy and robustness compared to traditional methods, providing a more effective solution for identifying anomalies in complex multivariate time series data.

关键词： Training Graph convolutional networks Industrial control Time series analysis Semantics Cause effect analysis Data models Robustness Bayes methods Anomaly detection

BPVFL: A Bidirectional Privacy-Preserving Verifiable Federated Learning Framework with Homomorphic Encryption

学校读者我要写书评

暂无评论

BPVFL: A Bidirectional Privacy-Preserving Verifiable Federat...

IEEE Conference on Global Communications (GLOBECOM)

作者： Jingwei Liu Sijing Chen Junrong Zhu Rong Sun Xiaojiang Du Mohsen Guizani Shaanxi Key Laboratory of Blockchain and Secure Computing Xidian University Xi’an China State Key Laboratory of ISN Xidian University Xi’an China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken USA Department of Machine Learning Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi UAE

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Federated learning, while advancing data privacy, faces risks of sensitive information leakage through parameter updates, making it susceptible to inference and data reconstruction attacks. Fraudulent behaviors by central servers or clients can undermine the integrity of model training, thereby reducing accuracy and affecting decision-making quality. This paper introduces a bidirectional, privacy-preserving verifiable federated learning framework(BPVFL) built on homomorphic encryption and a novel three-party zero-knowledge protocol. This framework guarantees the integrity of server aggregation and the credibility of the information uploaded by clients. Experimental results demonstrate that BPVFL effectively protects client privacy, prevents fraud by servers and certain clients, and efficiently handles numerous client disconnections with minimal overhead.

关键词： Training Privacy Protocols Federated learning Computational modeling Sampling methods Information leakage Robustness Servers Homomorphic encryption

Multi-Grained Feature Pruning for Video-Based Human Pose Estimation

学校读者我要写书评

暂无评论

Multi-Grained Feature Pruning for Video-Based Human Pose Est...

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

作者： Zhigang Wang Shaojing Fan Zhenguang Liu Zheqi Wu Sifan Wu Yingying Jiao College of Computer Science and Technology Zhejiang Gongshang University Hangzhou China School of Computing National University of Singapore Singapore The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou China College of Computer Science and Technology Jilin University Changchun China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing redundant temporal information and achieving fine-grained perception because they only focus on processing low-resolution features. To address these challenges, we propose a novel multi-scale resolution framework that encodes spatiotemporal representations at varying granularities and executes fine-grained perception compensation. Furthermore, we employ a density peaks clustering method to dynamically identify and prioritize tokens that offer important semantic information. This strategy effectively prunes redundant feature tokens, especially those arising from multi-frame features, thereby optimizing computational efficiency without sacrificing semantic richness. Empirically, it sets new benchmarks for both performance and efficiency on three large-scale datasets. Our method achieves a 93.8% improvement in inference speed compared to the baseline, while also enhancing pose estimation accuracy, reaching 87.4 mAP on the PoseTrack2017 dataset.

关键词： Accuracy Pose estimation Semantics Signal processing algorithms Benchmark testing Signal processing Motion capture Computational efficiency Spatiotemporal phenomena Speech processing

Quantum-based Variational Approach for Solving Graph Isomorphism Problems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Yukun Shen, Yingtong Zhang, Zhichao Wan, Linchun Beijing Key Laboratory of Petroleum Data Mining China University of Petroleum Beijing102249 China State Key Lab of Processors Institute of Computing Technology CAS Beijing100190 China School of Mathematics and Physics University of Science and Technology Beijing Beijing100083 China School of Computer and Information Science Southwest University Chongqing400715 China

The graph isomorphism problem remains a fundamental challenge in computer science, driving the search for efficient decision algorithms. Due to its ambiguous computational complexity, heuristic approaches such as simulated annealing are frequently used to explore the solution space selectively. These methods often achieve high probabilities of identifying solutions quickly, avoiding the exhaustive enumeration required by exact algorithms. However, traditional simulated annealing usually struggles with low sampling efficiency and reduced solution-finding probability in complex or large graph problems. In this study, we integrate the principles of quantum technology to address the graph isomorphism problem. By mapping the solution space to a quantum many-body system, we developed a parameterized model for variational simulated annealing. This approach emphasizes the regions of the solution space that are most likely to contain the optimal solution, thereby enhancing the search accuracy. Artificial neural networks were utilized to parameterize the quantum many-body system, leveraging their capacity for efficient function approximation to perform accurate sampling in the intricate energy landscapes of large graph problems. Copyright © 2025, The Authors. All rights reserved.

关键词： Heuristic methods

Modeling Fine-Grained Relations in Dynamic Space-Time Graphs for Video-Based Facial Expression Recognition

学校读者我要写书评

暂无评论

IEEE Transactions on Affective computing 2025年

作者： Huang, Changqin Jiang, Fan Han, Zhongmei Huang, Xiaodi Wang, Shijin Zhu, Yanlai Jiang, Yunliang Hu, Bin Zhejiang Normal University Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Jinhua321004 China Charles Sturt University School of Computing Mathematics and Engineering AlburyNSW2640 Australia State Key Laboratory of Cognitive Intelligence Anhui Hefei230088 China Hangzhou Hikvision Digital Technology Co. Ltd Education Business Department Hangzhou310051 China Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China Beijing Institute of Technology School of Medical Technology Beijing10081 China

Facial expressions in videos inherently mirror the dynamic nature of real-world facial events. Consequently, facial expression recognition (FER) should employ a dynamic graph-based representation to effectively capture the relational structure of facial expressions rather than relying on conventional grid or sequence methods. However, existing graph-based approaches have their limitations. Frame-level graph methods provide a coarse representation of the facial graph across time and space, while landmark-based graph methods need to introduce additional facial landmarks, resulting in a static graph structure. To address these challenges, we propose spatial-temporal relation-aware dynamic graph convolutional networks (ST-RDGCN). This fine-grained relation modeling approach enables the dynamic modeling of evolving facial expressions in videos through dynamic space-time graphs, eliminating the need for facial landmarks. ST-RDGCN encompasses three graph construction paradigms: dynamic independent space graph, dynamic joint space-time graph, and dynamic cross space-time graph. Furthermore, we propose a relation-aware space-time graph convolution (RSTG-Conv) operator to learn informative spatiotemporal correlations in dynamic space-time graphs. In extensive experimental evaluations, our ST-RDGCN demonstrates state-of-the-art performance on the five popular video-based FER datasets, achieving overall accuracy scores of 99.69%, 91.67%, 56.51%, 69.37%, and 49.03% on the CK+, Oulu-CASIA, AFEW, DFEW, and FERV39 k datasets, respectively. In particular, our ST-RDGCN outperforms the current best method by 3.6% in UAR on the most challenging FERV39 k dataset. Furthermore, our analysis reveals that the dynamic cross space-time graph scheme is the most effective among the three dynamic graph construction schemes. © 2010-2012 IEEE.

关键词： Graphic methods

Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Miao, Wenjun Pang, Guansong Li, Tianqi Bai, Xiao Zheng, Jin School of Computer Science and Engineering Beihang University China School of Computing and Information Systems Singapore Management University Singapore State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

Existing out-of-distribution (OOD) methods have shown great success on balanced datasets but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples are often wrongly classified into head classes and/or 2) tail-class samples are treated as OOD samples. To address these issues, current studies fit a prior distribution of auxiliary/pseudo OOD data to the long-tailed in-distribution (ID) data. However, it is difficult to obtain such an accurate prior distribution given the unknowingness of real OOD samples and heavy class imbalance in LTR. A straightforward solution to avoid the requirement of this prior is to learn an outlier class to encapsulate the OOD samples. The main challenge is then to tackle the aforementioned confusion between OOD samples and head/tail-class samples when learning the outlier class. To this end, we introduce a novel calibrated outlier class learning (COCL) approach, in which 1) a debiased large margin learning method is introduced in the outlier class learning to distinguish OOD samples from both head and tail classes in the representation space and 2) an outlier-class-aware logit calibration method is defined to enhance the long-tailed classification confidence. Extensive empirical results on three popular benchmarks CIFAR10-LT, CIFAR100-LT, and ImageNet-LT demonstrate that COCL substantially outperforms state-of-the-art OOD detection methods in LTR while being able to improve the classification accuracy on ID data. Code is available at https://***/mala-lab/COCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Quanjun Fang, Chunrong Zheng, Yi Zhang, Yaxin Zhao, Yuan Huang, Rubing Zhou, Jianyi Yang, Yun Zheng, Tao Chen, Zhenyu Department of Computing Technologies Swinburne University of Technology Melbourne Australia State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China School of Computer Science and Engineering Macau University of Science and Technology Jiangsu Nanjing China Huawei Cloud Computing Technologies Co. Ltd. Beijing China Shenzhen Research Institute of Nanjing University Guangdong Shenzhen China

Unit testing validates the correctness of the units of the software system under test and serves as the cornerstone in improving software quality and reliability. To reduce manual efforts in writing unit tests, some techniques have been proposed to generate test assertions automatically, including deep learning (DL)-based, retrieval-based, and integration-based ones. Among them, recent integration-based approaches inherit from both DL-based and retrieval-based approaches and are considered state-of-the-art. Despite being promising, such integration-based approaches suffer from inherent limitations, such as retrieving assertions with lexical matching while ignoring meaningful code semantics, and generating assertions with a limited training corpus. In this paper, we propose a novel Retrieval-Augmented Deep Assertion Generation approach, namely RetriGen, based on a hybrid assertion retriever and a pre-trained language model (PLM)-based assertion generator. Given a focal-test, RetriGen first builds a hybrid assertion retriever to search for the most relevant test-assert pair from external codebases. The retrieval process takes both lexical similarity and semantical similarity into account via a token-based and an embedding-based retriever, respectively. RetriGen then treats assertion generation as a sequence-to-sequence task and designs a PLM-based assertion generator to predict a correct assertion with historical test-assert pairs and the retrieved external assertion. Although our concept is general and can be adapted to various off-the-shelf encoder-decoder PLMs, we implement RetriGen to facilitate assertion generation based on the recent CodeT5 model. We conduct extensive experiments to evaluate RetriGen against six state-of-the-art approaches across two large-scale datasets and two metrics. The experimental results demonstrate that RetriGen achieves 57.66% and 73.24% in terms of accuracy and CodeBLEU, outperforming all baselines with an average improvement of 50.66

关键词： Semantics

Almost Optimal Time Lower Bound for Approximating Parameterized Clique, CSP, and More, under ETH

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guruswami, Venkatesan Lin, Bingkai Ren, Xuandi Sun, Yican Wu, Kewen Simons Institute for the Theory of Computing Departments of EECS and Mathematics UC Berkeley United States State Key Laboratory for Novel Software Technology Nanjing University China Department of EECS UC Berkeley United States School of Computer Science Peking University China

The Parameterized Inapproximability Hypothesis (PIH), which is an analog of the PCP theorem in parameterized complexity, asserts that, there is a constant Ε > 0 such that for any computable function f : N → N, no f(k) · nO(1)-time algorithm can, on input a k-variable CSP instance with domain size n, find an assignment satisfying 1 − Ε fraction of the constraints. A recent work by Guruswami, Lin, Ren, Sun, and Wu (STOC’24) established PIH under the Exponential Time Hypothesis (ETH). In this work, we improve the quantitative aspects of PIH and prove (under ETH) that approximating sparse parameterized CSPs within a constant factor requires nk1−o(1) time. This immediately implies that, assuming ETH, finding a (k/2)-clique in an n-vertex graph with a k-clique requires nk1−o(1) time. We also prove almost optimal time lower bounds for approximating k-ExactCover and Max k-Coverage. Our proof follows the blueprint of the previous work to identify a "vector-structured" ETH-hard CSP whose satisfiability can be checked via an appropriate form of "parallel" PCP. Using further ideas in the reduction, we guarantee additional structures for constraints in the CSP. We then leverage this to design a parallel PCP of almost linear size based on Reed-Muller codes and derandomized low degree testing. Copyright © 2024, The Authors. All rights reserved.

关键词： Blueprints

Ability of strong-pulse illumination to hack self-differencing avalanche photodiode detectors in a high-speed quantum-key-distribution system

学校读者我要写书评

暂无评论

Physical Review A 2022年第3期106卷 033713-033713页

作者： Binwu Gao Zhihao Wu Weixu Shi Yingwen Liu Dongyang Wang Chunlin Yu Anqi Huang Junjie Wu Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha 410073 China China Greatwall Research Institute China Greatwall Technology Group Co. Ltd. Shenzhen 518057 China

Implementation of high-speed quantum key distribution (QKD) has become one of the major focuses in the field, which produces a high key-generation rate for applications. To achieve high-speed QKD, tailored techniques are developed and employed to quickly generate and detect quantum states. However, these techniques may introduce unique loopholes to compromise the security of QKD systems. In this paper, we investigate the loopholes of the self-differencing (SD) avalanche photodiode (APD) detector, typically used for high-speed detection in a QKD system, and demonstrate experimental testing of the SD APD detector under strong-pulse-illumination attack. This attack presents blinding stability and helps an eavesdropper to learn the secret key without introducing extra quantum bit rate error. Based on this testing, we propose a set of criteria for protecting SD APD detectors from the strong-pulse-illumination attack.

关键词： Quantum communication Quantum cryptography