Improving Subgraph Recognition with Variational Graph Information Bottleneck | |
Yu, Junchi; Cao, Jie; He, Ran | |
2022 | |
会议名称 | Conference on Computer Vision and Pattern Recognition |
会议日期 | 2022 |
会议地点 | 美国路易斯安那新奥尔良 |
出版者 | IEEE Computer Society |
摘要 | Subgraph recognition aims at discovering a compressed substructure of a graph that is most informative to the graph property. It can be formulated by optimizing Graph Information Bottleneck (GIB) with a mutual information estimator. However, GIB suffers from training instability and de generated results due to its intrinsic optimization process. To tackle these issues, we reformulate the subgraph recognition problem into two steps: graph perturbation and sub graph selection, leading to a novel Variational Graph Information Bottleneck (VGIB) framework. VGIB first employs the noise injection to modulate the information flow from the input graph to the perturbed graph. Then, the perturbed graph is encouraged to be informative to the graph property. VGIB further obtains the desired subgraph by filtering out the noise in the perturbed graph. With the customized noise prior for each input, the VGIB objective is endowed with a tractable variational upper bound, leading to a superior empirical performance as well as theoretical properties. Extensive experiments on graph interpretation, explainability of Graph Neural Networks, and graph classification show that VGIB finds better subgraphs than existing methods. |
语种 | 英语 |
是否为代表性论文 | 否 |
七大方向——子方向分类 | 人工智能基础理论 |
国重实验室规划方向分类 | 多尺度信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57107 |
专题 | 模式识别实验室 |
通讯作者 | He, Ran |
作者单位 | 中国科学院自动化研究所 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yu, Junchi,Cao, Jie,He, Ran. Improving Subgraph Recognition with Variational Graph Information Bottleneck[C]:IEEE Computer Society,2022. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Yu 等 - 2022 - Improv(2212KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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。
修改评论