Structure-Enhanced Heterogeneous Graph Contrastive Learning | |
Zhu, Yanqiao1,2![]() ![]() ![]() | |
2022-03 | |
会议名称 | The 2022 SIAM International Conference on Data Mining |
页码 | 82-90 |
会议日期 | 2022-3 |
会议地点 | Online |
会议录编者/会议主办者 | SIAM |
出版者 | SIAM |
摘要 | Recent years have seen a growing interest in Graph Contrastive Learning (GCL), which trains Graph Neural Network (GNN) model to discriminate similar and dissimilar pairs of nodes without human annotations. Most prior GCL work focuses on homogeneous graphs and little attention has been paid to Heterogeneous Graphs (HGs) that involve different types of nodes and edges. Moreover, earlier studies reveal that the explicit use of structure information of un- derlying graphs is useful for learning representations. Conventional GCL methods merely measure the likelihood of contrastive pairs according to node representations, which may not align with the true semantic similarities. How to leverage such structure information for GCL is not yet well-understood. To address the aforementioned challenges, this paper presents a novel method dubbed STructure- EnhaNced heterogeneous graph ContrastIve Learning, STENCIL for brevity. At first, we generate multiple semantic views for HGs based on metapaths. Unlike most methods that maximize the consis- tency among these views, we propose a novel multiview contrastive aggregation objective to adaptively distill information from each view. In addition, we advocate the explicit use of structure embed- ding, which enriches the model with local structural patterns of the underlying HGs, so as to better mine true and hard negatives for GCL. Empirical studies on three real-world datasets show that our proposed method consistently outperforms existing state-of-the-art methods and even surpasses several supervised counterparts. |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48469 |
专题 | 模式识别实验室 |
作者单位 | 1.Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3.School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China 4.Department of Computer Science, Emory University, GA, USA |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhu, Yanqiao,Xu, Yichen,Cui, Hejie,et al. Structure-Enhanced Heterogeneous Graph Contrastive Learning[C]//SIAM:SIAM,2022:82-90. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
sdm2022.pdf(598KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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