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. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
  4. 资源与环境信息系统国家重点实验室
  5. 外文论文
Graph Out-of-Distribution Generalization With Controllable Data Augmentation

文献类型：期刊论文

作者Lu, Bin2; Zhao, Ze2; Gan, Xiaoying2; Liang, Shiyu3; Fu, Luoyi4; Wang, Xinbing2; Zhou, Chenghu1
刊名IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
出版日期2024-11-01
卷号36期号:11页码:6317-6329
关键词Out-of-distribution generalization graph neural network domain generalization data augmentation Out-of-distribution generalization graph neural network domain generalization data augmentation
ISSN号1041-4347
DOI10.1109/TKDE.2024.3393109
产权排序4
英文摘要Graph Neural Network (GNN) has demonstrated extraordinary performance in classifying graph properties. However, due to the selection bias of training and testing data (e.g., training on small graphs and testing on large graphs, or training on dense graphs and testing on sparse graphs), distribution deviation is widespread. More importantly, we often observe hybrid structure distribution shift of both scale and density, despite of one-sided biased data partition. The spurious correlations over hybrid distribution deviation degrade the performance of previous GNN methods and show large instability among different datasets. To alleviate this problem, we propose OOD-GMixup to jointly manipulate the training distribution with controllable data augmentation in metric space. Specifically, we first extract the graph rationales to eliminate the spurious correlations due to irrelevant information. Second, we generate virtual samples with perturbation on graph rationale representation domain to obtain potential OOD training samples. Finally, we propose OOD calibration to measure the distribution deviation of virtual samples by leveraging Extreme Value Theory, and further actively control the training distribution by emphasizing the impact of virtual OOD samples. Extensive studies on several real-world datasets on graph classification demonstrate the superiority of our proposed method over state-of-the-art baselines.
资助项目National Key R&D Program of China[2022YFB3904204] ; National Natural Science Foundation of China[623B2071] ; National Natural Science Foundation of China[42050105] ; National Natural Science Foundation of China[62272301] ; National Natural Science Foundation of China[62306179] ; National Natural Science Foundation of China[62020106005] ; National Natural Science Foundation of China[62061146002] ; National Natural Science Foundation of China[61960206002] ; Shanghai Pilot Program for Basic Research -Shanghai Jiao Tong University ; National Natural Science Fund for Excellent Young Scientists Fund Program (Overseas)
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001336378400119
出版者IEEE COMPUTER SOC
资助机构National Key R&D Program of China ; National Natural Science Foundation of China ; Shanghai Pilot Program for Basic Research -Shanghai Jiao Tong University ; National Natural Science Fund for Excellent Young Scientists Fund Program (Overseas)
源URL[http://ir.igsnrr.ac.cn/handle/311030/210521]  
专题资源与环境信息系统国家重点实验室_外文论文
通讯作者Gan, Xiaoying
作者单位1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100045, Peoples R China
2.Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
3.Shanghai Jiao Tong Univ, John Hopcroft Ctr Comp Sci, Shanghai 200240, Peoples R China
4.Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai 200240, Peoples R China
推荐引用方式
GB/T 7714		 Lu, Bin,Zhao, Ze,Gan, Xiaoying,et al. Graph Out-of-Distribution Generalization With Controllable Data Augmentation[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2024,36(11):6317-6329.
APA Lu, Bin.,Zhao, Ze.,Gan, Xiaoying.,Liang, Shiyu.,Fu, Luoyi.,...&Zhou, Chenghu.(2024).Graph Out-of-Distribution Generalization With Controllable Data Augmentation.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,36(11),6317-6329.
MLA Lu, Bin,et al."Graph Out-of-Distribution Generalization With Controllable Data Augmentation".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 36.11(2024):6317-6329.

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。