检索结果-内蒙古大学图书馆

DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Hourun Wang, Yifan Xiao, Zhiping Yang, Jia Zhou, Changling Zhang, Ming Ju, Wei State Key Laboratory for Multimedia Information Processing School of Computer Science PKU-Anker LLM Lab Peking University Beijing China Computer Center Peking University Beijing China School of Information Technology & Management University of International Business and Economics Beijing China Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States College of Computer Science Sichuan University Chengdu China

Recommender systems are widely used in various real-world applications, but they often encounter the persistent challenge of the user cold-start problem. Cross-domain recommendation (CDR), which leverages user interactions from one domain to improve prediction performance in another, has emerged as a promising solution. However, users with similar preferences in the source domain may exhibit different interests in the target domain. Therefore, directly transferring embeddings may introduce irrelevant source-domain collaborative information. In this paper, we propose a novel graph-based disentangled contrastive learning framework to capture fine-grained user intent and filter out irrelevant collaborative information, thereby avoiding negative transfer. Specifically, for each domain, we use a multi-channel graph encoder to capture diverse user intents. We then construct the affinity graph in the embedding space and perform multi-step random walks to capture high-order user similarity relationships. Treating one domain as the target, we propose a disentangled intent-wise contrastive learning approach, guided by user similarity, to refine the bridging of user intents across domains. Extensive experiments on four benchmark CDR datasets demonstrate that DisCo consistently outperforms existing state-of-the-art baselines, thereby validating the effectiveness of both DisCo and its components. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

GUARD: Multigranularity-based Unsupervised Anomaly Detection Algorithm for Multivariate Time Series 8

学校读者我要写书评

暂无评论

GUARD: Multigranularity-based Unsupervised Anomaly Detection...

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Meng, Fan Yang, Qunli He, Zhengda Yang, Shangdong Tang, Weidong Public Credit Information Center Jiangsu Strategy and Development Research Center Nanjing China Nanjing University State Key Lab for Novel Software Technology Nanjing China China Pharmaceutical University School of Science Nanjing China The School of Computer Science Nanjing University of Posts and Teleconnnunications Nanjing China China Telecom Corporation Limited Nanjing Branch Customer Operations Department Nanjing China

ISBN: (纸本)9781665477352

Unsupervised anomaly detection on multivariate time series (MTS) is a valuable problem in practice because it significantly reduces labeling costs. Even though most classical methods begin to consider inter-series dependencies, the hierarchical relationships between and within-series data are often ignored. To overcome these limitations, in this paper, we propose a multiGranUlArity based unsupeRvised anomaly Detection (GUARD) algorithm that captures the hierarchical relationships in three granularities and merges these dependencies in the following anomaly detection task. Specifically, the proposed algorithm first captures the internal dependencies within the subsequence and learns a hidden representation based on a trained autoencoder. Then, a hierarchical mechanism is designed to capture the local and global dependencies between the given subsequence and the whole set and learn their hidden representation. The experimental results show that the proposed algorithm can effectively and stably exploit the potential relationship of MTS and detect anomalies more accurately than the basic approaches. © 2022 IEEE.

关键词： Anomaly detection

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ji, Jiahao Wang, Jingyuan Jiang, Zhe Jiang, Jiawei Zhang, Hu State Key Laboratory of Software Development Environment School of Computer Science & Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Department of Computer & Information Science & Engineering The University of Florida United States MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science & Engineering Beihang University Beijing China

High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities. The lack of integration between physical principles and data-driven models is an important reason for limiting the development of this field. In the literature, physics-based methods can usually provide a clear interpretation of the dynamic process of traffic flow systems but are with limited accuracy, while data-driven methods, especially deep learning with black-box structures, can achieve improved performance but can not be fully trusted due to lack of a reasonable physical basis. To bridge the gap between purely data-driven and physics-driven approaches, we propose a physics-guided deep learning model named Spatio- Temporal Differential Equation Network (STDEN), which casts the physical mechanism of traffic flow dynamics into a deep neural network framework. Specifically, we assume the traffic flow on road networks is driven by a latent potential energy field (like water flows are driven by the gravity field), and model the spatio-temporal dynamic process of the potential energy field as a differential equation network. STDEN absorbs both the performance advantage of data-driven models and the interpretability of physics-based models, so is named a physics-guided prediction model. Experiments on three real-world traffic datasets in Beijing show that our model outperforms state-of-the-art baselines by a significant margin. A case study further verifies that STDEN can capture the mechanism of urban traffic and generate accurate predictions with physical meaning. The proposed framework of differential equation network modeling may also cast light on other similar applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Differential equations

Towards Fully Decoupled End-to-End Person Search

学校读者我要写书评

暂无评论

Towards Fully Decoupled End-to-End Person Search

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Pengcheng Zhang Xiao Bai Jin Zheng Xin Ning School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University Beijing China Institute of Semiconductors Chinese Academy of Sciences Cognitive Computing Technology Joint Laboratory Wave Group Beijing China

End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id task discriminates different identities, resulting in conflict optimal objectives. Existing works proposed to decouple end-to-end person search to alleviate such conflict. Yet these methods are still sub-optimal on one or two of the sub-tasks due to their partially decoupled models, which limits the overall person search performance. In this paper, we propose to fully decouple person search towards optimal person search. A task-incremental person search network is proposed to incrementally construct an end-to-end model for the detection and re-id sub-task, which decouples the model architecture for the two sub-tasks. The proposed task-incremental network allows task-incremental training for the two conflicting tasks. This enables independent learning for different objectives thus fully decoupled the model for personsearch. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed fully decoupled models for end-to-end person search.

关键词：

zsLLMCode: An Effective Approach for Code Embedding via LLM with Zero-Shot Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xian, Zixiang Huang, Rubing Cui, Chenhui Fang, Chunrong Chen, Zhenyu School of Computer Science and Engineering Macau University of Science and Technology Macau Taipa999078 China Macau University of Science and Technology Zhuhai MUST Science and Technology Research Institute Guangdong Zhuhai519099 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210093 China

The advent of large language models (LLMs) has greatly advanced artificial intelligence (AI) in software engineering (SE), with code embeddings playing a critical role in tasks like code-clone detection and code clustering. However, existing methods for code embedding, including those based on LLMs, often depend on costly supervised training or fine-tuning for domain adaptation. This paper proposes a novel zero-shot approach, zsLLMCode, to generate code embeddings by using LLMs and sentence embedding models. This approach attempts to eliminate the need for task-specific training or fine-tuning, and to effectively address the issue of erroneous information commonly found in LLM-generated outputs. We conducted a series of experiments to evaluate the performance of the proposed approach by considering various LLMs and embedding models. The results have demonstrated the effectiveness and superiority of our method zsLLMCode over state-of-the-art unsupervised approaches such as SourcererCC, Code2vec, InferCode, and TransformCode. Our findings highlight the potential of zsLLMCode to advance the field of SE by providing robust and efficient solutions for code embedding tasks. © 2024, CC BY.

关键词： Zero-shot learning

Abstract Syntax Tree for Programming Language Understanding and Representation: How Far Are We?

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Weisong Fang, Chunrong Miao, Yun You, Yudu Yuan, Mengzhe Chen, Yuchen Zhang, Quanjun Guo, An Chen, Xiang Liu, Yang Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing210093 China School of Computer Science and Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Nantong University Jiangsu Nantong226019 China

Programming language understanding and representation (a.k.a code representation learning) has always been a hot and challenging task in the field of software engineering. It aims to apply deep learning techniques to produce numerical representations of the source code features while preserving its semantics. These representations can be used for facilitating subsequent code-related tasks, e.g., code summarization. The abstract syntax tree (AST), a fundamental code feature, illustrates the syntactic information of the source code and has been widely used in code representation learning. It is commonly acknowledged that AST-based code representation is critical to solving code-related tasks. However, there is still a lack of systematic and quantitative evaluation of how well AST-based code representation facilitates subsequent code-related tasks. Additionally, learning an AST-based code representation is an extremely complex endeavor involving three intertwining stages, including, AST parsing, AST preprocessing, and AST encoding. The solutions available inMSC Codes 68-04, 68T30 Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

科学研究的第五范式——以智能驱动的材料设计为例

学校读者我要写书评

暂无评论

engineering 2023年第5期24卷 126-137,I0003,I0004页

作者： Can Leng Zhuo Tang Yi-Ge Zhou Zean Tian Wei-Qing Huang Jie Liu Keqin Li Kenli Li Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 410073China Laboratory of Software Engineering for Complex Systems National University of Defense TechnologyChangsha 410073China National Supercomputing Center in Changsha Changsha 410082China College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China Institute of Chemical Biology and Nanomedicine State Key Laboratory of Chemo/Biosensing and ChemometricsCollege of Chemistry and Chemical EngineeringHunan UniversityChangsha 410082China Department of Applied Physics School of Physics and ElectronicsHunan UniversityChangsha 410082China Department of Computer Science State University of New YorkNew PaltzNY 12561USA

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地... 详细信息

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地阐明了第五范式的本质,旨在促进第五范式在其他领域的培养。第五范式平台主要包括模型自动构建(原始数据提取)、指纹自动构建(神经网络特征选择)以及跨学科知识串联的重复迭代(“火山图”)。与分解一起进行的是对迭代中实现的体系结构的性能评估。通过讨论,第五范式的智能驱动平台可以极大地简化和改进研究中极其繁琐和具有挑战性的工作,并通过补偿机器学习中缺少样本和替代一些由于计算资源不足而导致的数值计算来实现数值计算与机器学习之间的相互反馈,从而加速探索过程。在数据驱动的学科中,跨学科专家的协同作用和对动态数据需求的急剧增长仍然是一个挑战。我们相信,对第五范式平台的一瞥可以为其在其他领域的应用铺平道路。

关键词：机器学习自动构建天河一号数据驱动神经网络动态数据知识整合科学研究

Towards Fully Decoupled End-to-End Person Search

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Pengcheng Zheng, Jin Bai, Xiao Ning, Xin School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University Beijing China Institute of Semiconductors Chinese Academy of Sciences Cognitive Computing Technology Joint Laboratory Wave Group Beijing China

End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id task discriminates different identities, resulting in conflict optimal objectives. Existing works proposed to decouple end-to-end person search to alleviate such conflict. Yet these methods are still sub-optimal on one or two of the sub-tasks due to their partially decoupled models, which limits the overall person search performance. In this paper, we propose to fully decouple person search towards optimal person search. A task-incremental person search network is proposed to incrementally construct an end-to-end model for the detection and re-id sub-task, which decouples the model architecture for the two sub-tasks. The proposed task-incremental network allows task-incremental training for the two conflicting tasks. This enables independent learning for different objectives thus fully decoupled the model for persons earch. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed fully decoupled models for end-to-end person search. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Multi-modal Multi-kernel Graph Learning for Autism Prediction and Biomarker Discovery

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Jin Mao, Junbin Lin, Hanhe Kuang, Hulin Pan, Shirui Wu, Xusheng Xie, Shan Liu, Fei Pan, Yi Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi830000 China Hunan Province Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Science and Engineering University of Dundee DundeeDD1 4HN United Kingdom School of Information and Communication Technology Griffith University Gold CoastQLD4215 Australia Shenzhen Health Development Research and Data Management Center Shenzhen518109 China

Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal integration and heterogeneous information extractions from graphs, we propose a novel method called Multi-modal Multi-Kernel Graph Learning (MMKGL). To solve the problem of negative impact among modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging Data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology. The source code will be available at https://***/yutian0315/MMKGL. © 2023, CC BY-NC-ND.

关键词： Graph embeddings