检索结果-内蒙古大学图书馆

32nd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Fu, Dongqi Univ Illinois Dept Comp Sci Urbana IL 61801 USA

ISBN: (纸本)9798400701245

The complexity of relationships between entities is increasing in the era of big data, leading to a growing interest in graph (network) data, owing to its ability to encode intricate relational information. graph data mining and machine learning methods extract informative node and graph representations to support broad applications, which have been proven effective for various high-impact tasks in the fields such as computer vision, natural language processing, and recommendation systems. Despite their effectiveness, graph data mining and machine learning methods face practical challenges in real-world scenarios. First, the input graphs may change over time, making it necessary to integrate time-evolving information to enhance representation capabilities. Second, the input graphs may contain unreliable, noisy, or sub-optimal information, requiring researchers and practitioners to intentionally modify the graph topology and node features to improve downstream performance. Facing these two phenomena, our research works focus on natural and artificial dynamics for benefiting graph data mining and machine learning. In this paper, we will briefly introduce our recent works in investigative natural and artificial dynamics and point out some under-explored research problems in the interaction of these dynamics.

关键词： graph data mining graph Machine Learning Temporal graphs graph Augmentation

来源：评论

学校读者我要写书评

暂无评论

graph data mining in Recommender Systems 22nd

Graph Data Mining in Recommender Systems

引用

22nd International Conference on Web Information Systems Engineering (WISE)

作者： Chen, Hongxu Li, Yicong Yang, Haoran Univ Technol Sydney Sydney NSW Australia

ISBN: (纸本)9783030915605;9783030915599

With the rapid development of e-commerce, massive data is generated from various e-commerce platforms. Most of the generated data can be represented in the forms of graph, which is capable to demonstrate the complicated relations among various entities, for example, graphs describe the interactions history between users and items. It is critical for the platforms to mine graph data to formulate recommendation strategy to gain more profits. For instance, in a user-item interaction graph, we can utilize graph data mining techniques to capture users' behavioral patterns to make personalized recommendation strategies. graph data mining in recommendation is currently a research topic attracts more and more attentions from industry and academic fields. In this half-day tutorial, we will present some key graph data mining methods and its applications in recommendation. We hope to find out the directions for the future work and that more theoretical models can be applied under real-world scenarios.

关键词： graph data mining Recommender systems graph neural networks Explainable machine learning Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Temporal Feature mining in Dynamic graph of Brain Connectivity data

Temporal Feature Mining in Dynamic Graph of Brain Connectivi...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Liu, Tao Jing, Ming Zhang, Guangwei Zhang, Li Yu, Jiguo School of Computer Science and Technology Qilu University of Technology Jinan China Big Data Institute Qilu University of Technology Jinan China Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9798350337020

In recent years, the graph feature mining method of brain connection data based on graph theory has been regarded as a popular and universal technology in the field of neuroscience. How to mine valuable information from brain connection data has become a research hotspot. Current research shows that the pathogenic factors of attention deficit and hyperactivity disorder (ADHD) may be caused by the abnormal connection between brain network structures. In order to find out the pathogenic factors of ADHD patients, we also carried out frequent sub-graph mining on the connectivity graph data of brain functional network. By constantly adjusting the sup-port threshold, all the subgraphs of ADHD patients and healthy control group were mined, and the differences in brain region connectivity were successfully found out. By combining the recently introduced neural document embedding model with traditional pattern mining techniques, we regard the brain network connection structure graph as the document and frequent subgraph as the atomic unit of the embedding process. By learning the mapping, each graph can be mapped to a D-dimensional continuous vector. The mapping needs to capture the similarity between the graphs. Feature vectors can be used as the direct input of graph classification in many traditional machine learning methods. Finally, support vector machine in machine learning is used to verify the accuracy of classification, and the results show that the accuracy is high. © 2023 IEEE.

关键词： ADHD brain network identification fMRI Frequent subgraph mining graph data mining

来源：评论

学校读者我要写书评

暂无评论

data-Driven Dynamic graph Convolution Transformer Network Model for EEG Emotion Recognition Under IoMT Environment

引用

BIG data mining AND ANALYTICS 2025年第3期8卷 712-725页

作者： Jin, Xing Zhu, Fa Shen, Yu Jeon, Gwanggil Camacho, David Nanjing Forestry Univ Coll Informat Sci & Technol & Artificial Intellige Coinnovat Ctr Sustainable Forestry Southern China Nanjing 210037 Peoples R China Nanjing Forestry Univ Coinnovat Ctr Sustainable Forestry Southern China State Key Lab Tree Genet & Breeding Nanjing 210037 Peoples R China Incheon Natl Univ Dept Embedded Syst Engn Incheon 22012 South Korea Univ Politcn Madrid Comp Syst Engn Dept Madrid 28660 Spain

With the rapid progress in data-driven approaches, artificial intelligence, and big data analytics technologies, utilizing electroencephalogram (EEG) signals for emotion analysis in the field of the Internet of Medical Things can effectively assist in the diagnosis of specific diseases. While existing emotion analysis methods focus on the utilization of effective deep models for data-driven and big data analytics technology, they often struggle to extract long-range dependencies and accurately model local relationships within multi-channel EEG signals. In addition, the subjective scores of the subjects may not match the predefined emotional labels. To overcome these limitations, this paper proposes a new data-driven dynamic graph-embedded Transformer network (DGETN) that has emerged in different tasks of graph data mining for emotion analysis of EEG signals in the scene of IoMT. Firstly, we extract the frequency features differential entropy (DE) and use the linear dynamic system (LDS) method to alleviate the redundancy and noise information. Secondly, to effectively explore the long-range information and local modeling ability, a novel feature extraction module is designed by embedding the dynamic graph convolution operations in the Transformer encoder for mining the discriminant features of data. Moreover, the graph convolution operations can effectively exploit the spatial information between different channels. At last, we introduce the minimum category confusion (MCC) loss to alleviate the fuzziness of classification. We take two commonly used EEG sentiment analysis datasets as a study. The DGETN has achieved state-of-the-art accuracies of 99.38% on the SEED dataset, and accuracies of 99.24 % and 98.85% for valence and arousal prediction on the DEAP dataset, respectively.

关键词： Internet of Medical Things (IoMT) emotion analysis electroencephalogram (EEG) signals data-driven big data analytics graph convolution operation minimum category confusion (MCC) loss graph data mining

来源：评论

学校读者我要写书评

暂无评论

Negative-Free Self-Supervised Gaussian Embedding of graphs

引用

NEURAL NETWORKS 2025年 181卷 106846页

作者： Liu, Yunhui He, Tieke Zheng, Tao Zhao, Jianhua Nanjing Univ State Key Lab Novel Software Technol Nanjing 210023 Peoples R China

graph Contrastive Learning (GCL) has recently emerged as a promising graph self-supervised learning framework for learning discriminative node representations without labels. The widely adopted objective function of GCL benefits from two key properties: alignment and uniformity, which align representations of positive node pairs while uniformly distributing all representations on the hypersphere. The uniformity property plays a critical role in preventing representation collapse and is achieved by pushing apart augmented views of different nodes (negative pairs). As such, existing GCL methods inherently rely on increasing the quantity and quality of negative samples, resulting in heavy computational demands, memory overhead, and potential class collision issues. In this study, we propose a negative-free objective to achieve uniformity, inspired by the fact that points distributed according to a normalized isotropic Gaussian are uniformly spread across the unit hypersphere. Therefore, we can minimize the distance between the distribution of learned representations and the isotropic Gaussian distribution to promote the uniformity of node representations. Our method also distinguishes itself from other approaches by eliminating the need fora parameterized mutual information estimator, an additional projector, asymmetric structures, and, crucially, negative samples. Extensive experiments over seven graph benchmarks demonstrate that our proposal achieves competitive performance with fewer parameters, shorter training times, and lower memory consumption compared to existing GCL methods.

关键词： graph neural networks graph representation learning Self-supervised learning graph data mining

来源：评论

学校读者我要写书评

暂无评论

graph Representation Learning via Contrasting Cluster Assignments

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2024年第3期16卷 912-922页

作者： Zhang, Chun-Yang Yao, Hong-Yu Chen, C. L. Philip Lin, Yue-Na Fuzhou Univ Coll Comp & Data Sci Fuzhou 350002 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China

With the rise of contrastive learning, unsupervised graph representation learning (GRL) has shown strong competitiveness. However, existing graph contrastive models typically either focus on the local view of graphs or take simple considerations of both global and local views. This may cause these models to overemphasize the importance of individual nodes and their ego networks, or to result in poor learning of global knowledge and affect the learning of local views. Additionally, most GRL models pay attention to topological proximity, assuming that nodes that are closer in graph topology are more similar. However, in the real world, close nodes may be dissimilar, which makes the learned embeddings incorporate inappropriate messages and thus lack discrimination. To address these issues, we propose a novel unsupervised GRL model by contrasting cluster assignments, called graph representation learning model via contrasting cluster assignment (GRCCA). To comprehensively explore the global and local views, it combines multiview contrastive learning and clustering algorithms with an opposite augmentation strategy. It leverages clustering algorithms to capture fine-grained global information and explore potential relevance between nodes in different augmented perspectives while preserving high-quality global and local information through contrast between nodes and prototypes. The opposite augmentation strategy further enhances the contrast of both views, allowing the model to excavate more invariant features. Experimental results show that GRCCA has strong competitiveness compared to state-of-the-art models in different graph analysis tasks.

关键词： Prototypes Clustering algorithms Representation learning Unsupervised learning Task analysis Topology Social networking (online) Contrastive learning graph data mining graph representation learning (GRL) unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Targeted k-node collapse problem: Towards understanding the robustness of local k-core structure

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2024年 641卷

作者： Lv, Yuqian Zhou, Bo Wang, Jinhuan Xuan, Qi Zhejiang Univ Technol Inst Cyberspace Secur Coll Informat Engn Hangzhou 310023 Peoples R China Binjiang Cyberspace Secur Inst ZJUT Hangzhou 310056 Peoples R China Zhejiang Inst Commun Dept Intelligent Control Hangzhou 311112 Peoples R China Qilu Univ Technol Shandong Acad Sci Key Lab Comp Power Network & Informat Secur Minist Educ Jinan 250353 Peoples R China

The concept of k-core, which indicates the largest induced subgraph where each node has k or more neighbors, plays a significant role in measuring the cohesiveness and engagement of a network, and it is exploited in diverse applications, e.g., network analysis, anomaly detection, community detection, etc. However, recent studies have demonstrated the vulnerability of kcore under malicious perturbations which focus on removing the minimal number of edges to make k-core structures collapse. Despite this, to the best of our knowledge, no existing research has yet concentrated on the minimal number of edges that must be removed to collapse a specific node in the k-core. To address this issue, in this paper, we make the first attempt to study the robustness of individual nodes in k-core and propose the Targeted k-node Collapse Problem (TNCP) with three novel contributions. Firstly, we offer a general definition of TNCP problem with a proof of its NP-hardness. Secondly, in order to cover the TNCP problem, we propose a heuristic algorithm named TNC and its improved version named ATNC for implementations on large-scale networks. Finally, experiments on 20 real-world networks across various domains verify the superiority of our proposed algorithms over 6 baseline methods with detailed comparisons and analyses. Resource related to our study is publicly available at https://***/Yocenly/TNCP.

关键词： k-core decomposition k-core robustness Adversarial attack Network science graph data mining

来源：评论

学校读者我要写书评

暂无评论

DeepInsight: Topology Changes Assisting Detection of Adversarial Samples on graphs

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第1期11卷 76-88页

作者： Zhu, Junhao Wang, Jinhuan Shan, Yalu Yu, Shanqing Chen, Guanrong Xuan, Qi Zhejiang Univ Technol Inst Cyberspace Secur Coll Informat Engn Hangzhou 310023 Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China PCL Res Ctr Networks & Commun Peng Cheng Lab Shenzhen 518000 Peoples R China Utron Technol Corp Ltd Hangzhou Qianjiang Distinguished Expert Hangzhou 310056 Peoples R China

With the rapid development of artificial intelligence, a number of machine learning algorithms, such as graph neural networks (GNNs), have been proposed to facilitate network analysis or graph data mining. Although effective, recent studies show that these advanced methods may suffer from adversarial attacks, i.e., they may lose effectiveness when only a small fraction of links are unexpectedly changed. This article investigates three well-known adversarial attack methods, i.e., Nettack, Meta Attack, and GradArgmax. It is found that different attack methods have their specific attack preferences on changing the target network structures. Such attack patterns are further verified by experimental results on some real-world networks, revealing that, generally, the top-4 most important network attributes on detecting adversarial samples suffice to explain the preference of an attack method. Based on these findings, the network attributes are utilized to design machine learning models for adversarial sample detection and attack method recognition with outstanding performance.

关键词： Feature extraction Anomaly detection Image edge detection Detectors Topology Task analysis Security Adversarial attack adversarial defense graph data mining network structure node classification social network

来源：评论

学校读者我要写书评

暂无评论

MONA: An Efficient and Scalable Strategy for Targeted k-Nodes Collapse

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2024年第6期71卷 3106-3110页

作者： Lv, Yuqian Zhou, Bo Wang, Jinhuan Yu, Shanqing Xuan, Qi Zhejiang Univ Technol Inst Cyberspace Secur Coll Informat Engn Hangzhou 310023 Peoples R China Binjiang Cyberspace Secur Inst ZJUT Hangzhou 310056 Peoples R China Zhejiang Inst Commun Dept Intelligent Control Hangzhou 311112 Peoples R China

The concept of k -core plays an important role in measuring the cohesiveness and engagement of a network. And recent studies have shown the vulnerability of k -core under adversarial attacks. However, there are few researchers concentrating on the vulnerability of individual nodes within k -core. Therefore, in this brief, we attempt to study Targeted k -Nodes Collapse Problem (TNsCP), which focuses on removing a minimal size set of edges to make multiple target k -nodes collapse. For this purpose, we first propose a novel algorithm named MOD for candidate reduction. Then we introduce an efficient strategy named MONA, based on MOD, to address TNsCP. Extensive experiments validate the effectiveness and scalability of MONA compared to several baselines. An open-source implementation is available at https://***/Yocenly/MONA .

关键词： Scalability Social networking (online) Security Research and development Perturbation methods Minimization Image edge detection k-core decomposition k-core robustness adversarial attack edge removal graph data mining

来源：评论

学校读者我要写书评

暂无评论

Disentangled graph Contrastive Learning With Independence Promotion

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2023年第8期35卷 7856-7869页

作者： Li, Haoyang Zhang, Ziwei Wang, Xin Zhu, Wenwu Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China

Self-supervised learning for graph neural networks has attracted considerable attention and shows notable successes in graph representation learning. However, the formation of a real-world graph typically arises from highly complex interactions of many latent factors. The existing self-supervised learning methods for GNNs are inherently holistic and neglect the entanglement of the latent factors, resulting in suboptimal learned representations for downstream tasks and difficult to be interpreted. Learning disentangled graph representations with self-supervised learning poses great challenges and remains largely ignored by the existing literature. In this paper, we introduce Independence Promoted Disentangled graph Contrastive Learning (IDGCL) method, which can learn disentangled graph-level representations with self-supervision. In particular, we first identify the latent factors of the input graph and derive its factorized representations. Then we propose a factor-wise discrimination objective in a contrastive learning manner, which can force the factorized representations to independently reflect the expressive information from different latent factors. To further promote the independence between the representations, we employ the Hilbert-Schmidt Independence Criterion to eliminate the dependence among different representations, which is effectively integrated into the self-supervised framework as a regularizer. Extensive experiments on synthetic and real-world datasets demonstrate the superiority of our method against several state-of-the-art baselines.

关键词： graph data mining graph neural network self-supervised learning disentangled representation learning

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：