Dual-Optimized Adaptive Graph Reconstruction for Multi-View Graph Clustering

计算机科学 聚类分析 图形 对偶(语法数字) 对偶图 人工智能 理论计算机科学 折线图 文学类 艺术
作者
Zichen Wen,Tianyi Wu,Yazhou Ren,Yawen Ling,Chenhang Cui,Xiaorong Pu,Lifang He
标识
DOI:10.1145/3664647.3680677
摘要

Multi-view clustering is an important machine learning task for multi-media data, encompassing various domains such as images, videos, and texts. Moreover, with the growing abundance of graph data, the significance of multi-view graph clustering (MVGC) has become evident. Most existing methods focus on graph neural networks (GNNs) to extract information from both graph structure and feature data to learn distinguishable node representations. However, traditional GNNs are designed with the assumption of homophilous graphs, making them unsuitable for widely prevalent heterophilous graphs. Several techniques have been introduced to enhance GNNs for heterophilous graphs. While these methods partially mitigate the heterophilous graph issue, they often neglect the advantages of traditional GNNs, such as their simplicity, interpretability, and efficiency. In this paper, we propose a novel multi-view graph clustering method based on dual-optimized adaptive graph reconstruction, named DOAGC. It mainly aims to reconstruct the graph structure adapted to traditional GNNs to deal with heterophilous graph issues while maintaining the advantages of traditional GNNs. Specifically, we first develop an adaptive graph reconstruction mechanism that accounts for node correlation and original structural information. To further optimize the reconstruction graph, we design a dual optimization strategy and demonstrate the feasibility of our optimization strategy through mutual information theory. Numerous experiments demonstrate that DOAGC effectively mitigates the heterophilous graph problem.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
邵之城发布了新的文献求助10
刚刚
1秒前
Owen应助沈自耕采纳,获得10
1秒前
2秒前
科研通AI6.4应助ojw21采纳,获得10
2秒前
3秒前
邸泽阳完成签到,获得积分10
3秒前
3秒前
科研小白完成签到,获得积分20
3秒前
4秒前
哇哇哇哇发布了新的文献求助10
4秒前
4秒前
4秒前
6秒前
飞飞发布了新的文献求助10
6秒前
LY发布了新的文献求助10
6秒前
6秒前
椰子应助plateauman采纳,获得10
6秒前
一朵风中摇曳的陈俊生完成签到,获得积分10
6秒前
科研小白发布了新的文献求助10
7秒前
失眠霸完成签到,获得积分10
7秒前
7秒前
MAXDONE完成签到,获得积分10
7秒前
余其钵发布了新的文献求助10
7秒前
我是老大应助787878采纳,获得10
8秒前
优秀的微笑完成签到 ,获得积分10
8秒前
汉堡包应助正直的夜天采纳,获得10
9秒前
万能图书馆应助Aan采纳,获得10
9秒前
10秒前
10秒前
打打应助木南采纳,获得10
11秒前
靓丽的胜发布了新的文献求助10
11秒前
11秒前
顾旻发布了新的文献求助10
12秒前
汉堡包应助哇哇哇哇采纳,获得10
12秒前
隐形曼青应助lulu采纳,获得10
13秒前
徐向成发布了新的文献求助10
13秒前
kyou完成签到,获得积分10
13秒前
14秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Industrial Hydraulics Manual (7th edition) 800
Physiologic races of the downy mildew fungus on soybeans in North Carolina 800
Rosenblum, Global Change Biology 800
Essentials of Carbohydrate Chemistry and Biochemistry, 4th Edition 800
Organizational Behavior 510
Management and the Arts 510
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 化学工程 工程类 有机化学 物理 复合材料 生物化学 内科学 细胞生物学 基因 遗传学 免疫学 冶金 光电子学 癌症研究
热门帖子
关注 科研通微信公众号,转发送积分 7776421
求助须知:如何正确求助?哪些是违规求助? 9317867
关于积分的说明 20360689
捐赠科研通 7363158
什么是DOI,文献DOI怎么找? 3318349
关于科研通互助平台的介绍 2466356
邀请新用户注册赠送积分活动 2333730