Graph Aggregating-Repelling Network: Do Not Trust All Neighbors in Heterophilic Graphs
文献类型：期刊论文
| 作者 | Wang, Yuhu1,2 ; Wen, Jinyong1,2; Zhang, Chunxia3; Xiang, Shiming1,2
|
| 刊名 | NEURAL NETWORKS
 |
| 出版日期 | 2024-10-01 |
| 卷号 | 178页码:13 |
| 关键词 | Graph neural network Homophily and heterophily Graph representation learning |
| ISSN号 | 0893-6080 |
| DOI | 10.1016/j.neunet.2024.106484 |
| 通讯作者 | Zhang, Chunxia(cxzhang@bit.edu.cn) |
| 英文摘要 | Graph neural networks (GNNs) have demonstrated exceptional performance in processing various types of graph data, such as citation networks and social networks, etc. Although many of these GNNs prove their superiority in handling homophilic graphs, they often overlook the other kind of widespread heterophilic graphs, in which adjacent nodes tend to have different classes or dissimilar features. Recent methods attempt to address heterophilic graphs from the graph spatial domain, which try to aggregate more similar nodes or prevent dissimilar nodes with negative weights. However, they may neglect valuable heterophilic information or extract heterophilic information ineffectively, which could cause poor performance of downstream tasks on heterophilic graphs, including node classification and graph classification, etc. Hence, a novel framework named GARN is proposed to effectively extract both homophilic and heterophilic information. First, we analyze the shortcomings of most GNNs in tackling heterophilic graphs from the perspective of graph spectral and spatial theory. Then, motivated by these analyses, a Graph Aggregating -Repelling Convolution (GARC) mechanism is designed with the objective of fusing both low-pass and high-pass graph filters. Technically, it learns positive attention weights as a low-pass filter to aggregate similar adjacent nodes, and learns negative attention weights as a high-pass filter to repel dissimilar adjacent nodes. A learnable integration weight is used to adaptively fuse these two filters and balance the proportion of the learned positive and negative weights, which could control our GARC to evolve into different types of graph filters and prevent it from over -relying on high intra-class similarity. Finally, a framework named GARN is established by simply stacking several layers of GARC to evaluate its graph representation learning ability on both the node classification and image -converted graph classification tasks. Extensive experiments conducted on multiple homophilic and heterophilic graphs and complex real -world image -converted graphs indicate the effectiveness of our proposed framework and mechanism over several representative GNN baselines. |
| WOS关键词 | CONVOLUTIONAL NETWORKS |
| 资助项目 | National Key Research and Development Program of China[2018AAA0100400] ; National Natural Science Foundation of China[62072039] ; National Natural Science Foundation of China[62076242] |
| WOS研究方向 | Computer Science ; Neurosciences & Neurology |
| 语种 | 英语 |
| WOS记录号 | WOS:001264207900001 |
| 出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59178]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
| 通讯作者 | Zhang, Chunxia |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Beijing Inst Technol, Sch Comp Sci Technol, Beijing 100081, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Yuhu,Wen, Jinyong,Zhang, Chunxia,et al. Graph Aggregating-Repelling Network: Do Not Trust All Neighbors in Heterophilic Graphs[J]. NEURAL NETWORKS,2024,178:13. |
| APA | Wang, Yuhu,Wen, Jinyong,Zhang, Chunxia,&Xiang, Shiming.(2024).Graph Aggregating-Repelling Network: Do Not Trust All Neighbors in Heterophilic Graphs.NEURAL NETWORKS,178,13. |
| MLA | Wang, Yuhu,et al."Graph Aggregating-Repelling Network: Do Not Trust All Neighbors in Heterophilic Graphs".NEURAL NETWORKS 178(2024):13. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。