中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Recognizing Predictive Substructures With Subgraph Information Bottleneck

文献类型：期刊论文

作者Yu, Junchi1; Xu, Tingyang2; Rong, Yu3; Bian, Yatao3; Huang, Junzhou3; He, Ran1,4
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2024-03-01
卷号46期号:3页码:1650-1663
关键词Three-dimensional displays Mutual information Task analysis Optimization Training Redundancy Computer vision Graph convolutional network subgraph information bottleneck graph classification
ISSN号0162-8828
DOI10.1109/TPAMI.2021.3112205
通讯作者He, Ran(rhe@nlpr.ia.ac.cn)
英文摘要The emergence of Graph Convolutional Network (GCN) has greatly boosted the progress of graph learning. However, two disturbing factors, noise and redundancy in graph data, and lack of interpretation for prediction results, impede further development of GCN. One solution is to recognize a predictive yet compressed subgraph to get rid of the noise and redundancy and obtain the interpretable part of the graph. This setting of subgraph is similar to the information bottleneck (IB) principle, which is less studied on graph-structured data and GCN. Inspired by the IB principle, we propose a novel subgraph information bottleneck (SIB) framework to recognize such subgraphs, named IB-subgraph. However, the intractability of mutual information and the discrete nature of graph data makes the objective of SIB notoriously hard to optimize. To this end, we introduce a bilevel optimization scheme coupled with a mutual information estimator for irregular graphs. Moreover, we propose a continuous relaxation for subgraph selection with a connectivity loss for stabilization. We further theoretically prove the error bound of our estimation scheme for mutual information and the noise-invariant nature of IB-subgraph. Extensive experiments on graph learning and large-scale point cloud tasks demonstrate the superior property of IB-subgraph.
资助项目Beijing Natural Science Foundation
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001174191100011
出版者IEEE COMPUTER SOC
资助机构Beijing Natural Science Foundation
源URL[http://ir.ia.ac.cn/handle/173211/58082]  
专题多模态人工智能系统全国重点实验室
通讯作者He, Ran
作者单位1.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China
2.Tencent AI LAB, Machine Learning Ctr, Shenzhen 518000, Guangdong, Peoples R China
3.Tencent AI LAB, Shenzhen 518000, Guangdong, Peoples R China
4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100864, Peoples R China
推荐引用方式
GB/T 7714		 Yu, Junchi,Xu, Tingyang,Rong, Yu,et al. Recognizing Predictive Substructures With Subgraph Information Bottleneck[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2024,46(3):1650-1663.
APA Yu, Junchi,Xu, Tingyang,Rong, Yu,Bian, Yatao,Huang, Junzhou,&He, Ran.(2024).Recognizing Predictive Substructures With Subgraph Information Bottleneck.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,46(3),1650-1663.
MLA Yu, Junchi,et al."Recognizing Predictive Substructures With Subgraph Information Bottleneck".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 46.3(2024):1650-1663.

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。