检索结果-内蒙古大学图书馆

Privacy-Preserving Push-Pull Method for Decentralized Optimization via State Decomposition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cheng, Huqiang Liao, Xiaofeng Li, Huaqing Zhao, You Key Laboratory of Dependable Services Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

Distributed optimization is manifesting great potential in multiple fields, e.g., machine learning, control, and resource allocation. Existing decentralized optimization algorithms require sharing explicit state information among the agents, which raises the risk of private information leakage. To ensure privacy security, combining information security mechanisms, such as differential privacy and homomorphic encryption, with traditional decentralized optimization algorithms is a commonly used means. However, this would either sacrifice optimization accuracy or incur heavy computational burden. To overcome these shortcomings, we develop a novel privacy-preserving decentralized optimization algorithm, called PPSD, that combines gradient tracking with a state decomposition mechanism. Specifically, each agent decomposes its state associated with the gradient into two substates. One substate is used for interaction with neighboring agents, and the other substate containing private information acts only on the first substate and thus is entirely agnostic to other agents. For the strongly convex and smooth objective functions, PPSD attains a R-linear convergence rate. Moreover, the algorithm can preserve the agents’ private information from being leaked to honest-but-curious neighbors. Simulations further confirm the results. © 2023, CC BY.

关键词： Optimization

Technical Function-effect Based Patent Multi-to-One Negation Game Model 25

学校读者我要写书评

暂无评论

Technical Function-effect Based Patent Multi-to-One Negation...

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Du, Lu Liu, Weidong Xiao, Kaiyang Gao, Shixuan Han, Yong College of Computer Science Inner Mongolia University Hohhot China Institute of Scientific and Technical Information of China Beijing China Natl. and Loc. Jt. Eng. Res. Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China Inner Mongolia Intellectual Property Service Center Hohhot China

ISBN: (纸本)9781665405270

As the number of patent applications increases yearly, the negation relation between patents has become intertwined, which makes it difficult for constructing negation relation in patent examination manually. Therefore, how to automatically construct negation relation between patents has become the hot research. Constructing negation relation is the process of comparing technical features between patents, which depends on the technical features in the patent claims and the technical function-effect. Although there are many researches on patent one-to-one negation, few researches on patent multi-to-one negation. The research on negation relation of multi-to-one patents, has the following challenges: (1) the definition of patent features is ambiguous in comparison of negation relation;(2) the role of patent function-effect is often ignored in judgement of negation relation. To solve the above issues, we propose a technical function-effect based patent multi-to-one negation game model. In the model, we decompose patent technical features into technical utility and technical function-effect. Patent technical utility is mainly realized by using the valence theory in linguistics. After obtaining technical utility, we choose to have the same technical effect, express the technical features of different technical functions, and obtain the patent technical function-effect. Finally, we combine the technical utility and function-effect to construct a technical utility/function-effect game tree to judge the patent negation relation. According to the two-tailed test in the A/B-test, our model outperforms the baseline model in the evaluation measurement. This model can subsequently be used to calculate the portfolio value and the strategic value of the patents. © 2022 IEEE.

关键词： Patents and inventions

A DHR executor selection algorithm based on historical credibility and dissimilarity clustering

学校读者我要写书评

暂无评论

science China(information sciences) 2023年第11期66卷 288-301页

作者： Sisi SHAO Yimu JI Weili ZHANG Shangdong LIU Fei JIANG Zhigang CAO Fei WU Fukang ZENG Jun ZUO Longfei ZHOU School of Computer Science Nanjing University of Posts and Telecommunications Institue of High Performance Computing and Bigdata Nanjing University of Posts and Telecommunications Purple Mountain Laboratories Nanjing Center of HPC China Jiangsu HPC and Intelligent Processing Engineer Research Center School of Foreign Languages Information Engineering University The 28th Research Institute of China Electronics Technology Group Corporation

The security of the dynamic heterogeneous redundancy(DHR) architecture relies on the heterogeneity of its executors, which also defines the vulnerability of the mimic system. In order to select executors with reliable and significant dissimilarity as service executors, we propose a DHR executor selection algorithm based on historical credibility and dissimilarity clustering(HCDC), which adds two metrics of executor historical credibility and dissimilarity. First, to maximize the difference between heterogeneous executor pools,clustering is performed based on the dissimilarity of the executor. Second, the executor with the highest historical credibility is selected from the heterogeneous executor pool as the candidate pool. The historical credibility is dynamically updated by the negative feedback control based on the results of the multi-mode adjudicator. Finally, the dynamic scheduling algorithm selects the executors from the candidate pool to form the set of service executors. The simulation results demonstrate that, in comparison to existing methods,the algorithm reduces the attack success rate and average failure rate while increasing system reliability.

关键词： endogenous security mimic defense DHR executor selection historical credibility

Irrational-window-filter projection method and application to quasiperiodic Schrödinger eigenproblems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Kai Li, Xueyang Ma, Yao Zhang, Juan Zhang, Pingwen Zhou, Qi Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China School of Mathematics and Statistics Wuhan University Wuhan430072 China School of Mathematical Sciences Peking University Beijing100871 China

In this paper, we propose a new algorithm, the irrational-window-filter projection method (IWFPM), for quasiperiodic systems with concentrated spectral point distribution. Based on the projection method (PM), IWFPM filters out dominant spectral points by defining an irrational window and uses a corresponding index-shift transform to make the FFT available. The error analysis on the function approximation level is also given. We apply IWFPM to 1D, 2D, and 3D quasiperiodic Schrödinger eigenproblems (QSEs) to demonstrate its accuracy and efficiency. IWFPM exhibits a significant computational advantage over PM for both extended and localized quantum states. More importantly, by using IWFPM, the existence of Anderson localization in 2D and 3D QSEs is numerically *** Codes 35P05, 35J10, 65D15, 65T50, 81-08 © 2024, CC BY-NC-SA.

关键词： Wiener filtering

FACOS: Enabling Privacy Protection Through Fine-Grained Access Control with On-chain and Off-chain System

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Chao Hou, Cankun Jiang, Tianyu Ning, Jianting Qiao, Hui Wu, Yusen Fujian Provincial Key Laboratory of Data Intensive Computing the Key Laboratory of Intelligent Computing and Information Processing Fujian China The School of Computer Science and Technology Xidian University Shaanxi Xi’an710071 China The Department of Computer Science University of Miami MiamiFL33146 United States College of Computer and Cyber Security Fujian Normal University Fuzhou350007 China The Faculty of Data Science City University of Macau China

Data-driven landscape across finance, government, and healthcare, the continuous generation of information demands robust solutions for secure storage, efficient dissemination, and fine-grained access control. Blockchain technology emerges as a significant tool, offering decentralized storage while upholding the tenets of data security and accessibility. However, on-chain and off-chain strategies are still confronted with issues such as untrusted off-chain data storage, absence of data ownership, limited access control policy for clients, and a deficiency in data privacy and auditability. To solve these challenges, we propose a permissioned blockchain-based privacy-preserving fine-grained access control on-chain and off-chain system, namely FACOS. We applied three fine-grained access control solutions and comprehensively analyzed them in different aspects, which provides an intuitive perspective for system designers and clients to choose the appropriate access control method for their systems. Compared to similar work that only stores encrypted data in centralized or non-fault-tolerant IPFS systems, we enhanced off-chain data storage security and robustness by utilizing a highly efficient and secure asynchronous Byzantine fault tolerance (BFT) protocol in the off-chain environment. As each of the clients needs to be verified and authorized before accessing the data, we involved the Trusted Execution Environment (TEE)-based solution to verify the credentials of clients. Additionally, our evaluation results demonstrated that our system1 offers better scalability and practicality than other state-of-the-art designs. We deployed our system on Alibaba Cloud and Tencent Cloud and conducted multiple evaluations. The results indicate that it takes about 2.79 seconds for a client to execute the protocol for uploading and about 0.96 seconds for downloading. Compared to other decentralized systems, our system exhibits efficient latency for both download and upload operations.

关键词： Access control

AN EMPIRICAL ANALYSIS OF UNCERTAINTY IN LARGE LANGUAGE MODEL EVALUATIONS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xie, Qiujie Li, Qingqiu Yu, Zhuohao Zhang, Yuejie Zhang, Yue Yang, Linyi Zhejiang University China School of Engineering Westlake University China School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Peking University China Westlake Institute for Advanced Study China University College London United Kingdom Huawei Noah’s Ark Lab Hong Kong

As LLM-as-a-Judge emerges as a new paradigm for assessing large language models (LLMs), concerns have been raised regarding the alignment, bias, and stability of LLM evaluators. While substantial work has focused on alignment and bias, little research has concentrated on the stability of LLM evaluators. In this paper, we conduct extensive experiments involving 9 widely used LLM evaluators across 2 different evaluation settings to investigate the uncertainty in model-based LLM evaluations. We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes. With careful comparative analyses, we find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent. By utilizing uncertainty to enhance LLM’s reliability and detection capability in Out-Of-Distribution (OOD) data, we further fine-tune an uncertainty-aware LLM evaluator named ConfiLM using a human-annotated fine-tuning set and assess ConfiLM’s OOD evaluation ability on a manually designed test set sourced from the 2024 Olympics. Experimental results demonstrate that incorporating uncertainty as additional information during the fine-tuning phase can largely improve the model’s evaluation performance in OOD scenarios. The code and data are released at: https://***/hasakiXie123/LLM-Evaluator-Uncertainty. © 2025, CC BY-NC-SA.

关键词： Digital elevation model

LMVD: A Large-Scale Multimodal Vlog Dataset for Depression Detection in the Wild

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Lang Chen, Kai Zhao, Junnan Wang, Yimeng Pei, Ercheng Chen, Haifeng Jiang, Jiewei Zhang, Shiqing Zhang, Jie Wang, Zhongmin He, Tao Tiwari, Prayag The School of Computer Science and Technology Xi’an University of Posts and Telecommunications Shaanxi Xi’an710121 China The Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi’an710121 China The Xi’an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi’an710121 China The School of Electronic Engineering Xi’an University of Posts and Telecommunications Xi’an710121 China The College of Electronic Information and Artificial Intelligence Shaanxi University of Science and Technology Xi’an710016 China The Institute of Intelligent Information Processing Taizhou University Zhejiang Taizhou318000 China The School of Education Shenzhen University Shenzhen518060 China The School of Information Technology Halmstad University Halmstad Sweden

Depression can significantly impact many aspects of an individual’s life, including their personal and social functioning, academic and work performance, and overall quality of life. Many researchers within the field of affective computing are adopting deep learning technology to explore potential patterns related to the detection of depression. However, because of subjects’ privacy protection concerns, that data in this area is still scarce, presenting a challenge for the deep discriminative models used in detecting depression. To navigate these obstacles, a large-scale multimodal vlog dataset (LMVD), for depression recognition in the wild is built. In LMVD, which has 1823 samples with 214 hours of the 1475 participants captured from four multimedia platforms (Sina Weibo, Bilibili, Tiktok, and YouTube). A novel architecture termed MDDformer to learn the non-verbal behaviors of individuals is proposed. Extensive validations are performed on the LMVD dataset, demonstrating superior performance for depression detection. We anticipate that the LMVD will contribute a valuable function to the depression detection community. The data and code will released at the link: https://***/helang818/LMVD/. © 2024, CC BY-NC-ND.

关键词： Deep learning

A Novel Preference-Driven Dynamic Multi-Objective Evolutionary Algorithm for Solving Dynamic Multi-Objective Problems

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wang, Xueqing Zheng, Jinhua Hou, Zhanglu Liu, Yuan Zou, Juan Xia, Yizhang Yang, Shengxiang Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Computer Science School of Cyberspace Science of Xiangtan University Hunan Province Xiangtan China Faculty of School of Computer Science School of Cyberspace Science of Xiangtan University Xiangtan411105 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

Most studies in dynamic multi-objective optimization have predominantly focused on rapidly and accurately tracking changes in the Pareto optimal front (POF) and Pareto optimal set (POS) when the environment undergoes changes. However, there are real-world scenarios where it is necessary to simultaneously solve changing objective functions and satisfy the preference of Decision Makers (DMs). In particular, the DMs may be only interested in a partial region of the POF, known as the region of interest (ROI), rather than requiring the entire POF. To meet the challenge of simultaneously predicting a changing POF and/or POS and dynamic ROI, this paper proposes a new dynamic multi-objective evolutionary algorithm (DMOEAs) based on the preference. The proposed algorithm consists of three key components: an evolutionary direction adjustment strategy based on changing reference points to accommodate shifts in preferences, an angle-based search strategy for tracking the varying ROI, and a hybrid prediction strategy that combines linear prediction models and population manifold estimation within the ROI to ensure convergence and distribution in scenarios where preferences remain unchanged. Experimental studies conducted on 16 widely used benchmark problems and empirical results demonstrate the significant advantages of the proposed algorithm over existing state-of-the-art DMOEAs. © 2024, The Authors. All rights reserved.

关键词： Evolutionary algorithms

ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Zhaoliang Wu, Zhihao Sadikaj, Ylli Plant, Claudia Dai, Hong-Ning Wang, Shiping Cheung, Yiu-Ming Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Department of Computer Science Hong Kong Baptist University Hong Kong Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Faculty of Computer Science and with the research network Data Science @ Uni Vienna University of Vienna Vienna1090 Austria

Although Graph Neural Networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes via various message-passing mechanisms, the performance of GNNs is limited by poor generalization and fragile robustness caused by noisy and redundant graph data. As a prominent solution, Graph Augmentation Learning (GAL) has recently received increasing attention in the literature. Among the existing GAL approaches, edge-dropping methods that randomly remove edges from a graph during training are effective techniques to improve the robustness of GNNs. However, randomly dropping edges often results in bypassing critical edges. Consequently, the effectiveness of message passing is weakened. In this paper, we propose a novel adversarial edgedropping method (ADEdgeDrop) that leverages an adversarial edge predictor guiding the removal of edges, which can be flexibly incorporated into diverse GNN backbones. Employing an adversarial training framework, the edge predictor utilizes the line graph transformed from the original graph to estimate the edges to be dropped, which improves the interpretability of the edge-dropping method. The proposed ADEdgeDrop is optimized alternately by stochastic gradient descent and projected gradient descent. Comprehensive experiments on eight graph benchmark datasets demonstrate that the proposed ADEdgeDrop outperforms state-of-the-art baselines across various GNN backbones, demonstrating improved generalization and robustness. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning