检索结果-内蒙古大学图书馆

TP-GCL: graph contrastive learning from the tensor perspective

FRONTIERS IN NEUROROBOTICS 2024年 18卷 1381084页

作者： Li, Mingyuan Meng, Lei Ye, Zhonglin Yang, Yanglin Cao, Shujuan Xiao, Yuzhi Zhao, Haixing Qinghai Normal Univ Coll Comp Xining Peoples R China State Key Lab Tibetan Intelligent Informat Proc & Xining Peoples R China

graph Neural Networks (GNNs) have demonstrated significant potential as powerful tools for handling graph data in various fields. However, traditional GNNs often encounter limitations in information capture and generalization when dealing with complex and high-order graph structures. Concurrently, the sparse labeling phenomenon in graph data poses challenges in practical applications. To address these issues, we propose a novel graph contrastive learning method, TP-GCL, based on a tensor perspective. The objective is to overcome the limitations of traditional GNNs in modeling complex structures and addressing the issue of sparse labels. Firstly, we transform ordinary graphs into hypergraphs through clique expansion and employ high-order adjacency tensors to represent hypergraphs, aiming to comprehensively capture their complex structural information. Secondly, we introduce a contrastive learning framework, using the original graph as the anchor, to further explore the differences and similarities between the anchor graph and the tensorized hypergraph. This process effectively extracts crucial structural features from graph data. Experimental results demonstrate that TP-GCL achieves significant performance improvements compared to baseline methods across multiple public datasets, particularly showcasing enhanced generalization capabilities and effectiveness in handling complex graph structures and sparse labeled data.

关键词： graph neural network graph contrastive learning complex structure hypergraph high-order adjacency tensor

来源：评论

学校读者我要写书评

暂无评论

PeerG: A P2P botnet detection method based on representation learning and graph contrastive learning

引用

COMPUTERS & SECURITY 2024年 140卷

作者： Wu, Guangli Wang, Xingyue Zhang, Jing Gansu Univ Polit Sci & Law Sch Cyberspace Secur Lanzhou 730070 Peoples R China

P2P botnets are distributed with complex topology and communication behavior, making them harder to detect and remove. Individuals or organizations can effectively detect P2P botnets by analyzing abnormal behaviors in network traffic. Existing works focus on extracting deterministic traffic interaction features, which are highly dependent on statistical features. Moreover, these methods are mainly aimed at generalized botnet detection and lack specificity for detecting P2P botnets. They ignore the topological information of P2P botnets, resulting in unsatisfactory detection accuracy. Among the few existing methods targeting P2P botnets, they consider the topological information but mainly rely on classical graph theory statistical features, such as degree, feature vector centrality, etc. This limits the generalization ability of the detection model. In this paper, we delve into the topological features of P2P botnets from the perspective of complex graph theory. We propose a P2P botnet detection method that combines representation learning and graph contrastive learning, dubbed PeerG. Specifically, we construct the communication graphs based on the flow interaction behavior between components of the P2P botnets. The Line algorithm is employed to embed the nodes of the communication graph into a low -dimensional representation vector space. Subsequently, the graph contrastive learning approach is utilized to optimize the feature extractor, enabling it to capture more representative node features. PeerG serves as a benchmark detection model for identifying P2P botnet nodes. Additionally, we devise two optimized contrastive detection strategies (PeerG-PreG and PeerG-PreF) based on graph -level and feature -level to boost the performance of PeerG. Extensive experiments demonstrate that PeerG brings significant improvements in detection accuracy over state -of -art detection methods. Furthermore, compared with PeerG, the detection strategies PeerG-PreG and PeerG-PreF hav

关键词： P2P botnet detection Representation learning graph contrastive learning Communication graph Topology information

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised graph contrastive learning With Virtual Adversarial Augmentation

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第8期36卷 4232-4244页

作者： Dong, Yixiang Luo, Minnan Li, Jundong Liu, Ziqi Zheng, Qinghua Xi An Jiao Tong Univ Sch Comp Sci & Technol Xian 710049 Peoples R China Univ Virginia Dept Elect & Comp Engn Dept Comp Sci Charlottesville VA 22904 USA Ant Grp AI Dept Hangzhou 310013 Zhejiang Peoples R China

Semi-supervised graph learning aims to improve learning performance by leveraging unlabeled nodes. Typically, it can be approached in two different ways, including predictive representation learning (PRL) where unlabeled data provide clues on input distribution and label-dependent regularization (LDR) which smooths the output distribution with unlabeled nodes to improve generalization. However, most existing PRL approaches suffer from overfitting in an end-to-end setting or cannot encode task-specific information when used as unsupervised pre-training (i.e., two-stage learning). Meanwhile, LDR strategies often introduce redundant and invalid data perturbations that can slow down and mislead the training. To address all these issues, we propose a general framework SemiGraL for semi-supervised learning on graphs, which bridges and facilitates both PRL and LDR in a single shot. By extending a contrastive learning architecture to the semi-supervised setting, we first develop a semi-supervised contrastive representation learning process with virtual adversarial augmentation to map input nodes into a label-preserving representation space while avoiding overfitting. We then introduce a multiview consistency classification process with well-constrained perturbations to achieve adversarially robust classification. Extensive experiments on seven semi-supervised node classification benchmark datasets show that SemiGraL outperforms various baselines while enjoying strong generalization and robustness performance.

关键词： Perturbation methods Task analysis Representation learning Training Manifolds Bridges Self-supervised learning graph contrastive learning semi-supervised graph learning virtual adversarial augmentation

来源：评论

学校读者我要写书评

暂无评论

PT4Rec: a universal prompt-tuning framework for graph contrastive learning-based recommendations

引用

MACHINE learning 2025年第3期114卷 1-20页

作者： Xiao, Wei Zhou, Qifeng Xiamen Univ Dept Automat Xiamen Peoples R China

graph contrastive learning-based recommendations have attracted a lot of research attention due to their exceptional performance. However, these approaches, which hinge on the optimization of downstream recommendations, often deviate from the original purpose of graph contrastive learning (i.e., learning embeddings independently of downstream tasks) and result in inconsistent performance. Some researchers have attempted to address this issue through prompt tuning, but the use of single and fixed prompts has shown limited efficacy and a lack of robustness across various benchmarks. To bridge the gap between graph contrastive learning and recommendation tasks, this paper proposes a universal Prompt-Tuning framework called PT4Rec. PT4Rec constructs learnable multi-prompts to capitalize on the flexibility of prompt tuning, thereby enhancing the robustness of graph contrastive learning-based recommendations in different scenarios. Specifically, PT4Rec first employs graph contrastive learning to enhance the pre-training embeddings of user and item nodes. Then it integrates multiple prompts derived from user profile inputs with user embeddings by the attention mechanism for prompt-tuning on downstream recommendation tasks. PT4Rec extends the prompt-tuning technique to adapt to various recommendation scenarios and constructs learnable multi-prompts to achieve better recommendation performance and scalability. Experimental validation on four benchmark datasets demonstrates the effectiveness of PT4Rec. The code is released at https://***/xiaowei-i/PT4Rec.

关键词： graph contrastive learning graph neural network Prompt-tuning Recommender system

来源：评论

学校读者我要写书评

暂无评论

MDFCL: Multimodal data fusion-based graph contrastive learning framework for molecular property prediction

引用

PATTERN RECOGNITION 2025年 163卷

作者： Gong, Xu Liu, Maotao Liu, Qun Guo, Yike Wang, Guoyin Chongqing Univ Posts & Telecommun Chongqing Key Lab Computat Intelligence Chongqing 400065 Peoples R China Hong Kong Univ Sci & Technol Clear Water Bay Kowloon Hong Kong 999077 Peoples R China

Molecular property prediction is a critical task with substantial applications for drug design and repositioning. The multiplicity of molecular data modalities and paucity of labeled data present significant challenges that affect algorithmic performance in this domain. Nevertheless, conventional approaches typically focus on singular data modalities and ignore either hierarchical structural features or other data pattern information, leading to problems when expressing complex phenomena and relationships. Additionally, the scarcity of labeled data obstructs the accurate mapping of instances to labels in property prediction tasks. To address these issues, we propose the Multimodal Data Fusion-based graph contrastive learning framework (MDFCL) for molecular property prediction. Specifically, we incorporate exhaustive information from dual molecular data modalities, namely graph and sequence structures. Subsequently, adaptive data augmentation strategies are designed based on the molecular backbones and side chains for multimodal data. Built upon these augmentation strategies, we develop a graph contrastive learning framework and pre-train it with unlabeled data (similar to 10M molecules). MDFCL is tested using 13 molecular property prediction benchmark datasets, demonstrating its effectiveness through empirical findings. In addition, a visualization study demonstrates that MDFCL can embed molecules into representative features and steer the distribution of molecular representations.

关键词： Molecular property prediction graph representation Multimodal data fusion graph contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Incorporating attributes and multi-scale structures for heterogeneous graph contrastive learning

引用

INFORMATION FUSION 2025年 122卷

作者： Jiang, Ruobing Li, Yacong Liu, Haobing Yu, Yanwei Ocean Univ China Dept Comp Sci & Technol Qingdao Peoples R China

Heterogeneous graphs (HGs) are composed of multiple types of nodes and edges, making it more effective in capturing the complex relational structures inherent in the real world. However, in real-world scenarios, labeled data is often difficult to obtain, which limits the applicability of semi-supervised approaches. As a result, this work leverages self-supervised learning to fully exploit unlabeled data and alleviate the problem of label scarcity. In this paper, we propose a novel contrastive learning framework for heterogeneous graphs (ASHGCL), which incorporates three distinct views: a low-order relation view that captures immediate neighborhood structures, a high-order relation view that models meta-path based relationships, and a feature similarity view that leverages node attribute information. To mitigate sampling bias, we design an attribute-enhanced positive sample selection strategy that integrates both structural and attribute information when generating positive pairs. Furthermore, we adopt local and global contrastive learning to capture knowledge at both node and graph levels, thereby enriching node representations at multiple granularities. Extensive experiments on four real-world datasets show that ASHGCL outperforms the state-of-the-art unsupervised baselines and even surpasses some supervised benchmarks.

关键词： Heterogeneous graph graph contrastive learning Data mining

来源：评论

学校读者我要写书评

暂无评论

Robust graph contrastive learning with multi-hop views for node classification

引用

APPLIED SOFT COMPUTING 2025年 171卷

作者： Wang, Yutong Zhang, Junheng Cao, Ren Zou, Minhao Guan, Chun Leng, Siyang Fudan Univ Inst AI & Robot Acad Engn & Technol Shanghai 200433 Peoples R China Fudan Univ Res Inst Intelligent Complex Syst Shanghai 200433 Peoples R China

contrastive learning has been proven successful in graph self-supervised learning by addressing label scarcity in real-world applications. Most existing methods fail to effectively incorporate multi-hop information into the augmented views but only focus on augmenting the raw input data, which incurs massive computational and memory costs. To address such limitations, we propose a novel approach, Multi-hop Views graph contrastive learning (MHVGCL), that enhances the node classification performance for graphs. Specifically, in contrast to existing methods that generate multiple augmented heads via neural networks, our approach generates these heads by exploiting multi-hop information, which is obtained iteratively from a single output head. This technique can extract more comprehensive structural information without destroying the graph topology. We further devise a multi-hop contrastive loss function to maximize agreements among the multi-hop views of the same node, while minimizing them among different nodes. This design contributes to more robust representation learning that keeps structural attributes invariant under different augmented views. Numerical experimental results on a variety of benchmarks demonstrate the significant superiority of our approach over other advanced methods, by learning more discriminative node representations even with extremely limited labels.

关键词： Self-supervised learning graph contrastive learning Multi-hop Node classification

来源：评论

学校读者我要写书评

暂无评论

Improving the quality of Positive and Negative Samples based on Topological Analysis and Counterfactual Reasoning for graph contrastive learning

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 277卷

作者： Wang, Xiaoyu Zhang, Qiqi Liu, Gen Zhao, Zhongying Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao 266590 Peoples R China

graph contrastive learning (GCL), as one of the most popular self-supervised paradigms, has achieved significant success in graph representation learning. However, its performance heavily depends on the quality of positive and negative samples. Thus, how to improve the quality of these samples becomes a very important and challenging problem. To address this issue, we propose a High-quality Positive and Negative Sampling Method based on Topological Analysis and Counterfactual Reasoning to Enhance graph contrastive learning(HiTCoGCL). It is a plug-and-play method that can be easily integrated into any GCL-based model. Firstly, we introduce a topology analysis-based method to selectively identify high-quality positive samples with high topological significance. Secondly, we design a counterfactual reasoning-based method to generate high-quality negative samples. The experimental results demonstrate that proposed HiTCo-GCL outperforms the existing state-ofthe-art methods, which verifies the effectiveness of the proposed method. The source codes of this work are available at https://***/ZZY-graphMiningLab/HiTCo-GCL.

关键词： graph neural networks graph contrastive learning Positive samples Negative samples

来源：评论

学校读者我要写书评

暂无评论

Deconvolution of spatial transcriptomics data via graph contrastive learning and partial least square regression

引用

BRIEFINGS IN BIOINFORMATICS 2025年第1期26卷 bbaf052页

作者： Mo, Yuanyuan Liu, Juan Zhang, Lihua Wuhan Univ Sch Artificial Intelligence Sch Comp Sci Wuhan 430072 Peoples R China

Deciphering the cellular abundance in spatial transcriptomics (ST) is crucial for revealing the spatial architecture of cellular heterogeneity within tissues. However, some of the current spatial sequencing technologies are in low resolutions, leading to each spot having multiple heterogeneous cells. Additionally, current spatial deconvolution methods lack the ability to utilize multi-modality information such as gene expression and chromatin accessibility from single-cell multi-omics data. In this study, we introduce a graph contrastive learning and Partial Least Squares regression-based method, CLPLS, to deconvolute ST data. CLPLS is a flexible method that it can be extended to integrate ST data and single-cell multi-omics data, enabling the exploration of the spatially epigenomic heterogeneity. We applied CLPLS to both simulated and real datasets coming from different platforms. Benchmark analyses with other methods on these datasets show the superior performance of CLPLS in deconvoluting spots in single cell level.

关键词： spatial transcriptomics cell type deconvolution single-cell multi-omics graph contrastive learning data integration

来源：评论

学校读者我要写书评

暂无评论

SGCL: Semi-supervised graph contrastive learning with confidence propagation algorithm for node classification

引用

KNOWLEDGE-BASED SYSTEMS 2024年 301卷

作者： Jiang, Wenhao Bai, Yuebin Beihang Univ Sch Comp Sci & Engn Beijing 100191 Peoples R China

Semi-Supervised graph learning (SSGL) aims to predict massive unknown labels based on a subset of known labels within a graph. Recently, graph neural network, one of the most popular SSGL approaches, has garnered considerable research interest and achieved remarkable progress. However, many of these methods perform unsatisfactorily with limited labeled data. graph contrastive learning (GCL), which utilizes unlabeled data to generate supervision, partially addresses this issue but does not fully exploit label information. To address this challenge, we propose SSGL algorithm, Semi-supervised graph contrastive learning with Confidence Propagation Algorithm (SGCL). SGCL comprises two stages of contrastive learning. In the first stage, we employ unsupervised contrastive learning to initialize the model with graph augmentation. In the second stage, in order to fully leverage known labels and graph structure, we incorporate supervised contrastive learning which utilizes supervision signals obtained from confidence propagation algorithm. By combining supervised contrastive learning and unsupervised contrastive learning, the embedding quality and the classification accuracy can be further enhanced. At last, comprehensive experiments demonstrate that SGCL outperforms the best baseline method by an average of 2.23% across six datasets, highlighting the effectiveness of our approach.

关键词： graph contrastive learning Label Propagation Algorithm Node classification Pseudo label

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：