检索结果-内蒙古大学图书馆

graph contrastive learning of modeling global-local interactions under hierarchical strategy: Application in anomaly detection

引用

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION 2025年 196卷

作者： Guo, Weiwei Wang, Yang Zhou, Le Jia, Mingwei Liu, Yi Zhejiang Univ Technol Inst Proc Equipment & Control Engn Hangzhou 310023 Peoples R China Shanghai Dianji Univ Sch Elect Engn Shanghai 200240 Peoples R China Zhejiang Univ Sci & Technol Sch Automat & Elect Engn Hangzhou 310023 Zhejiang Peoples R China

Lack of labeled samples and complexity of unit interactions pose significant challenges for effective anomaly detection in complex industrial processes. This work proposes an unsupervised anomaly detection framework, hierarchical strategy-based global-local graph contrastive learning (HS-GLGCL). First, a process topology graph is constructed based on prior knowledge and then enhanced by the technique of graph augmentation. The graph contrastive learning mechanism enables the model to learn intrinsic information from unlabeled samples. Local topological information is input into the model through structural coefficients to further accurately simulate information transmission between local variables amid complex unit interactions. When global topological information is found inadequately captured, isomorphic similarity is introduced to help the model obtain embeddings that can more accurately describe data distributions. Anomalies are detected and localized by setting a reconstruction error threshold. Additionally, reconstruction dissimilarity represented by Kullback-Leibler divergence is adopted to further confirm the model's performance superiority and complete a thorough evaluation of the model's reconstruction performance. The effectiveness of HS-GLGCL is validated in two case studies on data respectively from a sugar factory and a sour water treatment system.

关键词： Anomaly detection Topological isomorphism graph contrastive learning Process knowledge Process industry

来源：评论

学校读者我要写书评

暂无评论

graph contrastive learning for Multibehavior Recommendation

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2025年

作者： Ma, Gang-Feng Chen, Meng-Ang Yang, Xu-Hua Wen, Xilin Long, Haixia Huang, Yujiao Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Peoples R China Zhejiang Univ Technol Coll Zhijiang Shaoxing 312030 Peoples R China

Multibehavior collaborative filtering recommendations can significantly alleviate data sparsity issues caused by insufficient single-behavior information, enhancing recommendation performance. However, current multibehavior recommendation methods simply concatenate different behavior representations without further exploring the interactive information between behaviors, thus limiting recommendation effectiveness. To address the limitations, we propose the graph contrastive learning for multibehavior recommendation (GCMR) model. First, we use a shared bottom to capture the connections between different behaviors of each user. Then, we introduce a GCN-based multibehavior contrastive learning approach that employs cross-layer and cross-behavior contrastive learning to capture intrabehavior and cross-behavior network interaction information, which enhances user and item representations. Additionally, we propose a multibehavior feature fusion strategy that integrates user representations (and item representations) to fully exploit latent information of different behaviors and improve network representation performance. Extensive experiments on three open-source datasets demonstrate that the GCMR model outperforms the state-of-the-art, especially on the Tmall dataset, where GCMR achieved an improvement of 19.10% in HR@10 and 16.50% in NDCG@10 over the best baseline.

关键词： contrastive learning Data mining Cross layer design Recommender systems Noise Data models graph convolutional networks Attention mechanisms User preference Singular value decomposition graph contrastive learning graph neural network multibehavior feature fusion multibehavior recommendation

来源：评论

学校读者我要写书评

暂无评论

graph contrastive learning with multiple information fusion

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 268卷

作者： Wang, Xiaobao Yang, Jun Wang, Zhiqiang He, Dongxiao Zhao, Jitao Huang, Yuxiao Jin, Di Tianjin Univ Coll Intelligence & Comp Tianjin 300354 Peoples R China Guangdong Lab Artificial Intelligence & Digital Ec Shenzhen 518107 Peoples R China George Washington Univ Washington DC 20052 USA

graph contrastive learning has been extensively studied and achieved great success in many graph downstream tasks. Currently, some works try to construct positive and negative samples in an augmented-free manner. However, most existing methods are not completely augmented-free, such as manually setting the number of similar nodes, which is an alternative augmented mode and also causes certain information loss. Thus, we propose a novel completely Augmented-Free graph contrastive learning (C-AFGCL) framework with multitask constraints. Specifically, we use the first-order neighbors of anchor nodes as positive samples and other nodes directly as negative samples, therefore fully avoiding the augmentation procedure. Then, we design a global propagation matrix and perform information propagation and aggregation to achieve global information completion. Finally, we employ attribute reconstruction to mitigate the issue of node self-information loss caused by the extensive sharing of data between samples in the preceding process. Experiments on several datasets demonstrate that our proposed model achieves outstanding results. On average, our model surpasses the best baseline based on augmentation (GRACE) by 1.05% and the best baseline without augmentation (AFGRL) by 1.06% in node classification, while also outperforming supervised methods on all networks.

关键词： graph contrastive learning graph representation learning

来源：评论

学校读者我要写书评

暂无评论

graph contrastive learning for Clustering of Multi-Layer Networks

引用

IEEE TRANSACTIONS ON BIG DATA 2024年第4期10卷 429-441页

作者： Yang, Yifei Ma, Xiaoke Xidian Univ Sch Comp Sci & Technol Key Lab Smart Human Comp Interact & Wearable Techn Xian 710071 Peoples R China

Multi-layer networks precisely model complex systems in society and nature with various types of interactions, and identifying conserved modules that are well-connected in all layers is of great significance for revealing their structure-function relationships. Current algorithms are criticized for either ignoring the intrinsic relations among various layers, or failing to learn discriminative features. To attack these limitations, a novel graph contrastive learning framework for clustering of multi-layer networks is proposed by joining nonnegative matrix factorization and graph contrastive learning (called jNMF-GCL), where the intrinsic structure and discriminative of features are simultaneously addressed. Specifically, features of vertices are first learned by preserving the conserved structure in multi-layer networks with matrix factorization, and then jNMF-GCL learns an affinity structure of vertices by manipulating features of various layers. To enhance quality of features, contrastive learning is executed by selecting the positive and negative samples from the constructed affinity graph, which significantly improves discriminative of features. Finally, jNMF-GCL incorporates feature learning, construction of affinity graph, contrastive learning and clustering into an overall objective, where global and local structural information are seamlessly fused, providing a more effective way to describe structure of multi-layer networks. Extensive experiments conducted on both artificial and real-world networks have shown the superior performance of jNMF-GCL over state-of-the-art models across various metrics.

关键词： Clustering algorithms Network analyzers Representation learning Couplings Complex systems Big Data Analytical models Multi-layer networks graph clustering nonnegative matrix factorization graph contrastive learning

来源：评论

学校读者我要写书评

暂无评论

graph contrastive learning of subcellular-resolution spatial transcriptomics improves cell type annotation and reveals critical molecular pathways

引用

BRIEFINGS IN BIOINFORMATICS 2025年第1期26卷 bbaf020页

作者： Lu, Qiaolin Ding, Jiayuan Li, Lingxiao Chang, Yi Jilin Univ Sch Artificial Intelligence Qianjin St 2699 Changchun 130010 Peoples R China Michigan State Univ Dept Comp Sci & Engn 220 Trowbridge Rd E Lansing MI 48824 USA Boston Univ Commonwealth Ave Boston MA 02215 USA Jilin Univ Int Ctr Future Sci Qianjin St 2699 Changchun 130010 Peoples R China Jilin Univ Engn Res Ctr Knowledge Driven Human Machine Intell Qianjin St 2699 Changchun 130010 Peoples R China

Imaging-based spatial transcriptomics (iST), such as MERFISH, CosMx SMI, and Xenium, quantify gene expression level across cells in space, but more importantly, they directly reveal the subcellular distribution of RNA transcripts at the single-molecule resolution. The subcellular localization of RNA molecules plays a crucial role in the compartmentalization-dependent regulation of genes within individual cells. Understanding the intracellular spatial distribution of RNA for a particular cell type thus not only improves the characterization of cell identity but also is of paramount importance in elucidating unique subcellular regulatory mechanisms specific to the cell type. However, current cell type annotation approaches of iST primarily utilize gene expression information while neglecting the spatial distribution of RNAs within cells. In this work, we introduce a semi-supervised graph contrastive learning method called Focus, the first method, to the best of our knowledge, that explicitly models RNA's subcellular distribution and community to improve cell type annotation. Focus demonstrates significant improvements over state-of-the-art algorithms across a range of spatial transcriptomics platforms, achieving improvements up to 27.8% in terms of accuracy and 51.9% in terms of F1-score for cell type annotation. Furthermore, Focus enjoys the advantages of intricate cell type-specific subcellular spatial gene patterns and providing interpretable subcellular gene analysis, such as defining the gene importance score. Importantly, with the importance score, Focus identifies genes harboring strong relevance to cell type-specific pathways, indicating its potential in uncovering novel regulatory programs across numerous biological systems.

关键词： spatial transcriptomics graph contrastive learning cell type annotation subcellular gene neighborhood network

来源：评论

学校读者我要写书评

暂无评论

graph contrastive learning With Feature Augmentation for Rumor Detection

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第4期11卷 5158-5167页

作者： Li, Shaohua Li, Weimin Luvembe, Alex Munyole Tong, Weiqin Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China

While online social media brings convenience to people's communication, it has also caused the widespread spread of rumors and brought great harm. Recent deep-learning approaches attempt to identify rumors by engaging in interactive user feedback. However, the performance of these models suffers from insufficient and noisy labeled data. In this article, we propose a novel rumor detection model called graph contrastive learning with feature augmentation (FAGCL), which injects noise into the feature space and learns contrastively by constructing asymmetric structures. FAGCL takes user preference and news embedding as the initial features of the rumor propagation tree and then adopts a graph attention network to update node representations. To obtain the graph-level representation for rumor classification, FAGCL fuses multiple pooling techniques. Moreover, FAGCL adopts graph contrastive learning as an auxiliary task to constrain the representation consistency. contrastive learning on noisy data mines the supervision information of the rumor propagation tree itself, making the model more robust and effective. Results on two real-world datasets demonstrate that our proposed FAGCL model achieves significant improvements over the baseline models.

关键词： Feature extraction Training Task analysis Robustness Gaussian noise Social networking (online) Data mining Feature augmentation graph contrastive learning readout rumor detection

来源：评论

学校读者我要写书评

暂无评论

graph contrastive learning for Tracking Dynamic Communities in Temporal Networks

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2024年第5期8卷 3422-3435页

作者： Ai, Yun Xie, Xianghua Ma, Xiaoke Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China Xidian Univ Key Lab Smart Human Comp Interact & Wearable Tech Xian 710071 Peoples R China Swansea Univ Dept Comp Sci Swansea SA1 8EN W Glam Wales

Temporal networks are ubiquitous because complex systems in nature and society are evolving, and tracking dynamic communities is critical for revealing the mechanism of systems. Moreover, current algorithms utilize temporal smoothness framework to balance clustering accuracy at current time and clustering drift at historical time, which are criticized for failing to characterize the temporality of networks and determine its importance. To overcome these problems, we propose a novel algorithm by joining Non-negative matrix factorization and Contrastive learning for Dynamic Community detection (jNCDC). Specifically, jNCDC learns the features of vertices by projecting successive snapshots into a shared subspace to learn the low-dimensional representation of vertices with matrix factorization. Subsequently, it constructs an evolution graph to explicitly measure relations of vertices by representing vertices at current time with features at historical time, paving a way to characterize the dynamics of networks at the vertex-level. Finally, graph contrastive learning utilizes the roles of vertices to select positive and negative samples to further improve the quality of features. These procedures are seamlessly integrated into an overall objective function, and optimization rules are deduced. To the best of our knowledge, jNCDC is the first graph contrastive learning for dynamic community detection, that provides an alternative for the current temporal smoothness framework. Experimental results demonstrate that jNCDC is superior to the state-of-the-art approaches in terms of accuracy.

关键词： Heuristic algorithms Clustering algorithms Self-supervised learning Representation learning Windows Knowledge engineering Visualization Dynamic community graph contrastive learning non-negative matrix factorization self-representation temporal networks

来源：评论

学校读者我要写书评

暂无评论

graph contrastive learning with high-order feature interactions and adversarial Wasserstein-distance-based alignment

引用

INTERNATIONAL JOURNAL OF MACHINE learning AND CYBERNETICS 2024年 1-12页

作者： Wang, Chenxu Wan, Zhizhong Meng, Panpan Wang, Shihao Wang, Zhanggong Xi An Jiao Tong Univ Sch Software Engn Xian 710049 Peoples R China Xi An Jiao Tong Univ MoE Key Lab Intelligent Networks & Network Secur Xian 710049 Peoples R China

graph contrastive learning (GCL) has proven to be an effective approach for unsupervised representation learning on graph-structured data. However, existing GCL models face two major limitations. First, existing feature augmentation methods fail to capture the high-order interactions among raw features, which are essential for feature engineering. Second, effective strategies for extracting global information from graphs for contrastive learning remain limited. To address these limitations, we propose a novel GCL model with high-order feature interactions and adversarial Wasserstein-distance-based alignment. Our model employs DNNs to capture complex interactions among raw features and introduce an alignment-based loss function to effectively extract global graph information. While traditional methods for calculating Wasserstein distance between graph views are computationally intensive, we overcome this challenge by training an adversarial Wasserstein-distance discriminator that enables efficient distance computation. We conduct extensive experiments on five benchmark datasets to evaluate the performance of the proposed method. The experimental results demonstrate that our approach achieves superior performance on classification tasks.

关键词： graph contrastive learning Feature interaction Adversarial Wasserstein-distance-based alignment

来源：评论

学校读者我要写书评

暂无评论

graph contrastive learning with node-level accurate difference

引用

FUNDAMENTAL RESEARCH 2025年第2期5卷 818-829页

作者： Jiao, Pengfei Yu, Kaiyan Bao, Qing Jiang, Ying Guo, Xuan Zhao, Zhidong Hangzhou Dianzi Univ Sch Cyberspace Hangzhou 310018 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Hangzhou Dianzi Univ Data Secur Governance Zhejiang Engn Res Ctr Hangzhou 310018 Peoples R China

graph contrastive learning (GCL) has attracted extensive research interest due to its powerful ability to capture latent structural and semantic information of graphs in a self-supervised manner. Existing GCL methods commonly adopt predefined graph augmentations to generate two contrastive views. Subsequently, they design a contrastive pretext task between these views with the goal of maximizing their agreement. These methods assume the augmented graph can fully preserve the semantics of the original. However, typical data augmentation strategies in GCL, such as random edge dropping, may alter the properties of the original graph. As a result, previous GCL methods overlooked graph differences, potentially leading to difficulty distinguishing between graphs that are structurally similar but semantically different. Therefore, we argue that it is necessary to design a method that can quantify the dissimilarity between the original and augmented graphs to more accurately capture the relationships between samples. In this work, we propose a novel graph contrastive learning framework, named Accurate Difference-based Node-Level graph contrastive learning (DNGCL), which helps the model distinguish similar graphs with slight differences by learning node-level differences between graphs. Specifically, we train the model to distinguish between original and augmented nodes via a node discriminator and employ cosine dissimilarity to accurately measure the difference between each node. Furthermore, we employ multiple types of data augmentation commonly used in current GCL methods on the original graph, aiming to learn the differences between nodes under different augmentation strategies and help the model learn richer local information. We conduct extensive experiments on six benchmark datasets and the results show that our DNGCL outperforms most state-of-the-art baselines, which strongly validates the effectiveness of our model.

关键词： graph neural network graph contrastive learning Accurate difference measure Node representation learning Pretext task design

来源：评论

学校读者我要写书评

暂无评论

graph contrastive learning with graph Info-Min 23

Graph Contrastive Learning with Graph Info-Min

引用

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

作者： Meng, En Liu, Yong Heilongjiang Univ Haerbin Peoples R China

ISBN: (纸本)9798400701245

The complexity of the graph structure poses a challenge for graph representation learning. contrastive learning offers a straightforward and efficient unsupervised framework for graph representation learning. It achieves unsupervised learning by augmenting the original views and comparing them with the augmented views. Several methods based on this framework have achieved significant progress in the field of graph representation learning. Despite its success, the factors contributing to good augmented views in graph contrast learning have received less attention. In order to address this issue, we introduce the graph info-min principle. We investigate the relationship between mutual information (MI) and good augmented views through experimental and theoretical analysis. Additionally, we present a new contrastive learning method called Info-min contrastive learning (IMCL). Specifically, The method comprises an adaptive graph augmentation generator and a pseudo-label generator. The graph augmentation generator ensures sufficient differentiation between the augmented and original views. The pseudo-label generator generates pseudo-labels as supervision signals, ensuring consistency between the classification results of augmented views and original views. Our method demonstrates excellent performance through extensive experimental results on various datasets.

关键词： unsupervised learning graph contrastive learning deep clustering

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：