TY - GEN
T1 - GOOD-D
T2 - 16th ACM International Conference on Web Search and Data Mining, WSDM 2023
AU - Liu, Yixin
AU - Ding, Kaize
AU - Liu, Huan
AU - Pan, Shirui
N1 - Funding Information:
This work was supported by ARC Future Fellowship (No. FT210100097), Amazon Research Award, ONR (No. N00014-21-1-4002), ARO (No. W911NF2110030), ARL (No. W911NF2020124), and NSF (No. 2229461).
Publisher Copyright:
© 2023 ACM.
PY - 2023/2/27
Y1 - 2023/2/27
N2 - Most existing deep learning models are trained based on the closed-world assumption, where the test data is assumed to be drawn i.i.d. from the same distribution as the training data, known as in-distribution (ID). However, when models are deployed in an open-world scenario, test samples can be out-of-distribution (OOD) and therefore should be handled with caution. To detect such OOD samples drawn from unknown distribution, OOD detection has received increasing attention lately. However, current endeavors mostly focus on grid-structured data and its application for graph-structured data remains under-explored. Considering the fact that data labeling on graphs is commonly time-expensive and labor-intensive, in this work we study the problem of unsupervised graph OOD detection, aiming at detecting OOD graphs solely based on unlabeled ID data. To achieve this goal, we develop a new graph contrastive learning framework GOOD-D for detecting OOD graphs without using any ground-truth labels. By performing hierarchical contrastive learning on the augmented graphs generated by our perturbation-free graph data augmentation method, GOOD-D is able to capture the latent ID patterns and accurately detect OOD graphs based on the semantic inconsistency in different granularities (i.e., node-level, graph-level, and group-level). As a pioneering work in unsupervised graph-level OOD detection, we build a comprehensive benchmark to compare our proposed approach with different state-of-the-art methods. The experiment results demonstrate the superiority of our approach over different methods on various datasets.
AB - Most existing deep learning models are trained based on the closed-world assumption, where the test data is assumed to be drawn i.i.d. from the same distribution as the training data, known as in-distribution (ID). However, when models are deployed in an open-world scenario, test samples can be out-of-distribution (OOD) and therefore should be handled with caution. To detect such OOD samples drawn from unknown distribution, OOD detection has received increasing attention lately. However, current endeavors mostly focus on grid-structured data and its application for graph-structured data remains under-explored. Considering the fact that data labeling on graphs is commonly time-expensive and labor-intensive, in this work we study the problem of unsupervised graph OOD detection, aiming at detecting OOD graphs solely based on unlabeled ID data. To achieve this goal, we develop a new graph contrastive learning framework GOOD-D for detecting OOD graphs without using any ground-truth labels. By performing hierarchical contrastive learning on the augmented graphs generated by our perturbation-free graph data augmentation method, GOOD-D is able to capture the latent ID patterns and accurately detect OOD graphs based on the semantic inconsistency in different granularities (i.e., node-level, graph-level, and group-level). As a pioneering work in unsupervised graph-level OOD detection, we build a comprehensive benchmark to compare our proposed approach with different state-of-the-art methods. The experiment results demonstrate the superiority of our approach over different methods on various datasets.
KW - contrastive learning
KW - graph neural networks
KW - out-of-distribution detection
UR - http://www.scopus.com/inward/record.url?scp=85143576822&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85143576822&partnerID=8YFLogxK
U2 - 10.1145/3539597.3570446
DO - 10.1145/3539597.3570446
M3 - Conference contribution
AN - SCOPUS:85143576822
T3 - WSDM 2023 - Proceedings of the 16th ACM International Conference on Web Search and Data Mining
SP - 339
EP - 347
BT - WSDM 2023 - Proceedings of the 16th ACM International Conference on Web Search and Data Mining
PB - Association for Computing Machinery, Inc
Y2 - 27 February 2023 through 3 March 2023
ER -