检索结果-内蒙古大学图书馆

Heterogeneous data augmentation in graph contrastive learning for effective negative samples

COMPUTERS & ELECTRICAL ENGINEERING 2024年第PartA期118卷

作者： Ali, Adnan Li, Jinlong Chen, Huanhuan Univ Sci & Technol China Sch Comp Sci & Technol Jinzhai Rd Hefei 230026 Anhui Peoples R China

graph contrastive learning (GCL) aims to contrast positive-negative counterparts, whereas graph data augmentation (GDA) in GCL is employed to generate positive-negative samples. Existing GDA techniques, such as 1 -dimensional (1D) feature masking, suffer from having a high probability of augmenting partially homogeneous views. Homogeneous views encode identical embeddings, induce substandard positive-negative samples, and enforce the performance responsibility on structural augmentation. Thus, previous work requires plenty of negative samples, converges slower, consumes more memory for training, and offers trivial performance improvements on downstream tasks. To overcome these issues, firstly , we introduce a novel 2dimensional (2D) feature masking technique in GCL to mask the feature matrix in 2 -dimensions. Secondly , we introduce heterogeneous augmentation, a combination of 1D -2D feature masking and edge dropping. Thirdly , we present a negative samples -based GCL framework: Heterogeneous D ata A ugmentation in graph Contrastive Learning for E ffective N egative S amples ( DAENS ). The effectiveness of the DAENS's induced positive-negative samples can be quantified as using only inter -view negative samples improves node classification performance up to 5.84% on 8 benchmark datasets. DAENS converges faster, takes less time per epoch, and is more memory efficient than existing state-of-the-art methods. Lastly , we empirically examine the feature and structural augmentation effect on sparse and dense graphs with DAENS. The implementation of DAENS is available at https://***/mhadnanali/DAENS.

关键词： graph data augmentation graph representation learning graph contrastive learning Self-supervised learning graph machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards data augmentation in graph neural network: An overview and evaluation

引用

COMPUTER SCIENCE REVIEW 2023年 47卷

作者： Adjeisah, Michael Zhu, Xinzhong Xu, Huiying Ayall, Tewodros Alemu Zhejiang Normal Univ Coll Math & Comp Sci Jinhua 321004 Peoples R China Beijing Geekplus Technol Co Ltd Artificial Intelligence Res Inst Beijing 100101 Peoples R China

Many studies on graph data augmentation (GDA) approaches have emerged. The techniques have rapidly improved performance for various graph neural network (GNN) models, increasing the current state-of-the-art accuracy by absolute values of 4.20%, 5.50%, and 4.40% on Cora, Citeseer, and PubMed, respectively. The success is attributed to two integral properties of relational approaches: topology -level and feature-level augmentation. This work provides an overview of some GDA algorithms which are reasonably categorized based on these integral properties. Next, we engage the three most widely used GNN backbones (GCN, GAT, and graphSAGE) as plug-and-play methods for conducting experiments. We conclude by evaluating the algorithm's effectiveness to demonstrate significant differences among various GDA techniques based on accuracy and time complexity with additional datasets different from those used in the original works. While discussing practical and theoretical motivations, considerations, and strategies for GDA, this work comprehensively investigates the challenges and future direction by pinpointing several open conceivable issues that may require further study based on far-reaching literature interpretation and empirical outcomes.

关键词： Feature representation graph data augmentation graph neural network Topology augmentation

来源：评论

学校读者我要写书评

暂无评论

SMix-GNN:A Powerful graph Neural Network Enhanced by Aggregating graph Mixup and K-Reciprocal Nearest Neighbors

引用

Engineering Letters 2025年第5期33卷 1723-1734页

作者： Rong, Minxi Zhang, Guipeng Guo, Xiaoli Sun, Qi Hu, Fuyang Qi, Huijing College of Mathematics and Information Science Zhengzhou University of Light Industry Zhengzhou 450000 China

Current methods for imbalanced graph classification often overlook the complex interplay between network topology and node attributes, which leads to the inadequate extraction of structural features by the model. Although techniques such as undersampling or oversampling can help mitigate data imbalance, they often introduce noise, further blurring the distinction between majority and minority classes. To address these challenges, this paper introduces Structural Mixup GNN (SMix-GNN), a novel model for imbalanced graph classification using graph Neural Networks (GNNs). The proposed approach starts by constructing a k-Nearest Relational Neighbor (k-RNN) graph, utilizing topological similarity to enhance the capture of neighborhood structural features during message propagation. Next, edges are masked, and nodes from minority class graphs are randomly removed to generate augmented graphs, thereby enriching the feature space of minority class samples in the training set. Finally, the SMixup technique is applied, blending original graphs with their augmented versions to mitigate the risk of losing critical minority class information during model updates. Extensive experiments on five real-world datasets demonstrate the effectiveness of SMix-GNN, achieving improvements of up to 5.63% in F1 score and 2.84% in accuracy. These results highlight the model’s robustness and generalizability, ultimately contributing to superior classification performance. © 2025, International Association of Engineers. All rights reserved.

关键词： graph Classification graph data augmentation graph Neural Networks S-Mixup

来源：评论

学校读者我要写书评

暂无评论

Invariant Risk Minimization augmentation for graph Contrastive Learning 7th

Invariant Risk Minimization Augmentation for Graph Contrasti...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Qin, Peng Chen, Weifu Sun Yat Sen Univ Sch Math Guangzhou Peoples R China Sun Yat Sen Univ Guangdong Prov Key Lab Computat Sci Guangzhou Peoples R China Guangzhou Maritime Univ Dept Comp Sci Guangzhou Peoples R China

ISBN: (纸本)9789819785049;9789819785056

Despite significant advancements in graph Contrastive Learning (GCL) in recent years, effective and interpretable graph data augmentation methods remain a challenge in the field. Traditional graph augmentation methods typically involve randomly modifying node attributes, edge properties, or extracting subgraphs, with their fundamental principles and operations derived from random processing of image data. However, graph data lacks the Euclidean structure and attribute intuitiveness of image data, making it difficult to ensure that augmentation data retains key features. In this paper, we propose a novel method called Invariant Risk Minimization augmentation for graph Contrastive Learning (IRMGCL). IRMGCL incorporates invariant risk minimization loss during the training process to ensure that data augmentation methods preserve invariant features. Specifically, we use different augmentation channels as environmental variables and train these channels to maintain invariant features through different environments. Experiments conducted on citation network datasets Cora and Citeseer demonstrate the effectiveness of our method. We compared our method with state-of-the-art graph contrastive learning methods, showing superior performance. Simultaneously, we conducted ablation experiments to verify the role of each component loss function in IRMGCL. Furthermore, our framework can incorporate labeled data for semi-supervised contrastive learning. Our experiments show that model performance can be further enhanced.

关键词： graph data augmentation graph Contrastive Learning Invariant Risk Minimization Invariant Features

来源：评论

学校读者我要写书评

暂无评论

Explainability-based graph augmentation for out-of-distribution robustness in digital pathology

引用

Knowledge-Based Systems 2025年 320卷

作者： Heidari Gheshlaghi, Saba Aryal, Milan Yahya Soltani, Nasim Ganji, Masoud Department of Computer Science Marquette University MilwaukeeWI53233 United States Northshore Pathologists S.C. MilwaukeeWI53211 United States

Whole slide images (WSIs), which are high-resolution digital representations of tissue samples, present significant challenges for processing because of their gigapixel scale. Recent studies show that graph neural networks (GNNs), which leverage neighborhood information, can enhance cancer classification accuracy in WSIs. However, GNN performance is affected by out-of-distribution (OOD) data, which occurs when the training and testing data are from different sources. Detecting OOD samples in graph data is especially challenging due to its complexity, which makes GNNs vulnerable to performance degradation. To address this issue, we propose a novel data augmentation framework to improve GNN robustness against OOD samples. Our approach augments node features by sampling important subgraphs, simulating potential OOD scenarios during training. Experiments on three public WSI datasets demonstrate significant improvements in graph classification tasks on OOD samples. In this work, one dataset serves as the in-distribution benchmark, while the others represent OOD scenarios. These results highlight the potential of data augmentation to enhance GNN robustness against OOD samples, improving cancer classification in WSIs. © 2025 Elsevier B.V.

关键词： Adversarial attack Digital pathology Explainability graph data augmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient and Effective augmentation Framework With Latent Mixup and Label-Guided Contrastive Learning for graph Classification

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2024年第12期36卷 8066-8078页

作者： Zeng, Aoting Wang, Liping Zhang, Wenjie Lin, Xuemin East China Normal Univ Shanghai 200062 Peoples R China Univ New South Wales Sydney NSW 2052 Australia Shanghai Jiao Tong Univ Shanghai 200230 Peoples R China

Neural Networks (GNNs) with data augmentation obtain promising results among existing solutions for graph classification. Mixup-based augmentation methods for graph classification have already achieved state-of-the-art performance. However, existing mixup-based augmentation methods either operate in the input space and thus face the challenge of balancing efficiency and accuracy, or directly conduct mixup in the latent space without similarity guarantee, thus leading to lacking semantic validity and limited performance. To address these limitations, this paper proposes G-MixCon, a novel framework leveraging the strengths of Mix up-based augmentation and supervised Con trastive learning (SCL). To the best of our knowledge, this is the first attempt to develop an SCL-based approach for learning graph representations. Specifically, the mixup-based strategy within the latent space named GDAgl and GDAnl are proposed, which efficiently conduct linear interpolation between views of the node or graph level. Furthermore, we design a dual-objective loss function named SupMixCon that can consider both the consistency among graphs and the distances between the original and augmented graph. SupMixCon can guide the training process for SCL in G-MixCon while achieving a similarity guarantee. Comprehensive experiments are conducted on various real-world datasets, the results show that G-MixCon demonstrably enhances performance, achieving an average accuracy increment of 6.24%, and significantly increases the robustness of GNNs against noisy labels.

关键词： graph data augmentation graph classification graph classification graph contrastive learning graph contrastive learning graph contrastive learning

来源：评论

学校读者我要写书评

暂无评论

CC-GNN: A Clustering Contrastive Learning Network for graph Semi-Supervised Learning

引用

IEEE ACCESS 2024年 12卷 71956-71969页

作者： Qin, Peng Chen, Weifu Zhang, Min Li, Defang Feng, Guocan Sun Yat Sen Univ Sch Math Guangzhou 510275 Peoples R China Sun Yat sen Univ Guangdong Prov Key Lab Guangzhou 510275 Peoples R China Guangzhou Maritime Univ Coll Informat & Telecommun Engn Guangzhou 510725 Peoples R China Guangzhou Vocat Coll Technol & Business Guangzhou 511442 Peoples R China

In graph modeling, scarcity of labeled data is a challenging issue. To address this issue, state-of-the-art graph models learn the representation of graph data via contrastive learning. Those models usually use data augmentation techniques to generate positive pairs for contrastive learning, which aims to maximize the similarity of positive data pairs while minimizing the similarity of negative data pairs. However, samples with the same labels may be separately mapped in the feature space. To solve this problem, we introduce a novel model called Clustering Contrastive graph Neural Network (CC-GNN), which develops a new kind of grouped contrastive learning that maximizes the similarity of positive data groups and minimizes the similarity of negative groups. That is, contrastive learning is defined on a group level rather than on an instant level. We assert that parameters learned by this kind of contrastive learning will lead to better performance of graph neural networks for downstream classification tasks. We combined the clustering contrastive learning technique with three baseline GNN models for graph classification. We found that the performance of these models was significantly improved, which strongly supports our assertion. We also testified the models for node classification on three popular citation networks. Finally, we conducted an ablation study to analyze how the clustering contrastive learning influence the performance of a graph model.

关键词： data augmentation graph neural networks Clustering algorithms data models Semisupervised learning Analytical models Task analysis Clustering contrastive learning graph data augmentation graph neural networks semi-supervised graph learning

来源：评论

学校读者我要写书评

暂无评论

Controlled graph neural networks with denoising diffusion for anomaly detection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartB期237卷

作者： Li, Xuan Xiao, Chunjing Feng, Ziliang Pang, Shikang Tai, Wenxin Zhou, Fan Sichuan Univ Natl Key Lab Fundamental Sci Synthet Vis Chengdu 610065 Peoples R China Henan Univ Sch Comp & Informat Engn Kaifeng 475000 Peoples R China Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu 610054 Peoples R China Kash Inst Elect & Informat Ind Kashi 844199 Peoples R China Sichuan Post & Telecommun Coll Chengdu 610067 Peoples R China

Leveraging labels in a supervised learning framework as prior knowledge to enhance network anomaly detection has become a trend. Unfortunately, just a few labels are typically available due to the expensive labeling cost. The limited labeled data might not adequately represent the underlying distribution of the data, making the trained model fail to accurately detect anomalies in test data that fall outside the labeled data's distribution. Recently, data augmentation has been widely used to address this issue. However, general graph data augmentation methods might lead to suboptimal performance when directly applying to network anomaly detection as they might alter graph semantics. In this paper, we provide a denoising diffusion probabilistic model (DDPM)-based Controlled graph Neural Networks (ConGNN) that can address the problem of insufficient labeled data. In particular, we propose a graph-specific diffusion model-based generator which can inject the characteristics of a reference node into another source node. This generator is adopted to steer the procedure of neighborhood aggregation in GNN to build a controlled GNN for generating augmented data. Based on these augmented data, we present a data-enclosing hypersphere model with our designed consistency regularization term to perform anomaly detection. Extensive experiments demonstrate the superior performance of our model compared to the state-of-the-art baselines.

关键词： Anomaly detection graph data augmentation Diffusion models graph neural networks

来源：评论

学校读者我要写书评

暂无评论

MVGCNMDA: Multi-view graph augmentation Convolutional Network for Uncovering Disease-Related Microbes

引用

INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES 2022年第3期14卷 669-682页

作者： Hua, Meifang Yu, Shengpeng Liu, Tianyu Yang, Xue Wang, Hong Shandong Normal Univ Sch Informat Sci & Engn Jinan 250358 Peoples R China

Motivation: Exploring the interrelationships between microbes and disease can help microbiologists make decisions and plan treatments. Predicting new microbe-disease associations currently relies on biological experiments and domain knowledge, which is time-consuming and inefficient. Automated algorithms are used to uncover the intrinsic link between microbes and disease. However, due to data noise and inadequate understanding of relevant biology, the efficient prediction of microbe-disease associations is still crucial. This study develops a multi-view graph augmentation convolutional network (MVGCNMDA) to predict potential disease-associated microbes. Methods: First, we use two data augmentation methods, edge perturbation and node dropping, to remove the data noise in the preprocessing stage. Second, we calculate Gaussian interaction profile kernel similarity and cosine similarity. Therefore, the graph Convolutional Network(GCN) can fully use multi-view features. Then, the multi-view features are fed into the multi-attention block to learn the weights of different features adaptively. Finally, the embedding results are obtained using a Convolutional Neural Network (CNN) combiner, and the matrix completion is used to predict the relationship between potential microbes and diseases. Results: We test our model on the Human microbe-disease Association database (HMDAD), Disbiome, and the Combined dataset (Peryton and MicroPhenoDB). The area under PR curve (AUPR), area under ROC curve (AUC), F1 score, and RECALL value are calculated to evaluate the performance of the developed MVGCNMDA. The AUPR is 0.9440, AUC is 0.9428, F1 score is 0.9383, and RECALL value is 0.8858. The experiments show that our model can accurately predict potential microbe-disease associations compared with the state-of-the-art works on the global Leave-One-Out-Cross-Validation (LOOCV) and the fivefold Cross-Validation (fivefold CV). To further verify the effectiveness of the proposed graph data aug

关键词： microbe-disease associations graph data augmentation Multi-view graph convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Action Sequence augmentation for Early graph-based Anomaly Detection 21

Action Sequence Augmentation for Early Graph-based Anomaly D...

引用

30th ACM International Conference on Information and Knowledge Management (CIKM)

作者： Zhao, Tong Ni, Bo Yu, Wenhao Guo, Zhichun Shah, Neil Jiang, Meng Univ Notre Dame Notre Dame IN 46556 USA Snap Inc Santa Monica CA USA

ISBN: (纸本)9781450384469

The proliferation of web platforms has created incentives for online abuse. Many graph-based anomaly detection techniques are proposed to identify the suspicious accounts and behaviors. However, most of them detect the anomalies once the users have performed many such behaviors. Their performance is substantially hindered when the users' observed data is limited at an early stage, which needs to be improved to minimize financial loss. In this work, we propose Eland, a novel framework that uses action sequence augmentation for early anomaly detection. Eland utilizes a sequence predictor to predict next actions of every user and exploits the mutual enhancement between action sequence augmentation and user-action graph anomaly detection. Experiments on three real-world datasets show that Eland improves the performance of a variety of graph-based anomaly detection methods. With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.

关键词： graph machine learning Anomaly detection graph data augmentation

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：