Ada-MIP: Adaptive Self-supervised Graph Representation Learning via Mutual Information and Proximity Optimization
文献类型：期刊论文
| 作者 | Ren, Yuyang1; Zhang, Haonan1; Yu, Peng1; Fu, Luoyi1; Cao, Xinde1; Wang, Xinbing1; Chen, Guihai1; Long, Fei2; Zhou, Chenghu3 |
| 刊名 | ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
 |
| 出版日期 | 2023-06-01 |
| 卷号 | 17期号:5页码:23 |
| ISSN号 | 1556-4681 |
| 关键词 | Self-supervised learning semi-supervised learning graph neural network |
| DOI | 10.1145/3568165 |
| 通讯作者 | Ren, Yuyang(renyuyang@sjtu.edu.cn) |
| 英文摘要 | Self-supervised graph-level representation learning has recently received considerable attention. Given varied input distributions, jointly learning graphs' unique and common features is vital to downstream tasks. Inspired by graph contrastive learning (GCL), which targets maximizing the agreement between graph representations from different views, we propose an Adaptive self-supervised framework, Ada-MIP, considering both Mutual Information between views (unique features) and inter-graph Proximity (common features). Specifically, Ada-MIP learns graphs' unique information through a learnable and probably injective augmenter, which can acquire more adaptive views compared to the augmentation strategies applied by existing GCL methods; to learn graphs' common information, we employ graph kernels to calculate graphs' proximity and learn graph representations among which the precomputed proximity is preserved. By sharing a global encoder, graphs' unique and common information can be well integrated into the graph representations learned by Ada-MIP. Ada-MIP is also extendable to semi-supervised scenarios, with our experiments confirming its superior performance in both unsupervised and semi-supervised tasks. |
| 资助项目 | NSF China[42050105] ; NSF China[62020106005] ; NSF China[62061146002] ; NSF China[61960206002] ; 100-Talents Program of Xinhua News Agency ; Program of Shanghai Academic/Technology Research Leader[18XD1401800] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| 出版者 | ASSOC COMPUTING MACHINERY |
| WOS记录号 | WOS:000968706500009 |
| 资助机构 | NSF China ; 100-Talents Program of Xinhua News Agency ; Program of Shanghai Academic/Technology Research Leader |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/196967]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Ren, Yuyang |
| 作者单位 | 1.Shanghai Jiao Tong Univ, Shanghai, Peoples R China 2.Xinhua News Agcy, State Key Lab Media Convergence Prod Technol & Sy, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, 11 Datun Rd, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Ren, Yuyang,Zhang, Haonan,Yu, Peng,et al. Ada-MIP: Adaptive Self-supervised Graph Representation Learning via Mutual Information and Proximity Optimization[J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,2023,17(5):23. |
| APA | Ren, Yuyang.,Zhang, Haonan.,Yu, Peng.,Fu, Luoyi.,Cao, Xinde.,...&Zhou, Chenghu.(2023).Ada-MIP: Adaptive Self-supervised Graph Representation Learning via Mutual Information and Proximity Optimization.ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,17(5),23. |
| MLA | Ren, Yuyang,et al."Ada-MIP: Adaptive Self-supervised Graph Representation Learning via Mutual Information and Proximity Optimization".ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 17.5(2023):23. |
入库方式： OAI收割
来源：地理科学与资源研究所
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。