Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308671321> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4308671321 abstract "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." @default.
- W4308671321 created "2022-11-14" @default.
- W4308671321 creator A5008056593 @default.
- W4308671321 creator A5013881064 @default.
- W4308671321 creator A5043301109 @default.
- W4308671321 creator A5044455276 @default.
- W4308671321 date "2023-02-27" @default.
- W4308671321 modified "2023-10-01" @default.
- W4308671321 title "GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection" @default.
- W4308671321 cites W1179283095 @default.
- W4308671321 cites W2144182447 @default.
- W4308671321 cites W2906943923 @default.
- W4308671321 cites W3034213836 @default.
- W4308671321 cites W3094497296 @default.
- W4308671321 cites W3099152386 @default.
- W4308671321 cites W3159630167 @default.
- W4308671321 cites W4221166060 @default.
- W4308671321 cites W4318823295 @default.
- W4308671321 cites W4318828927 @default.
- W4308671321 doi "https://doi.org/10.1145/3539597.3570446" @default.
- W4308671321 hasPublicationYear "2023" @default.
- W4308671321 type Work @default.
- W4308671321 citedByCount "5" @default.
- W4308671321 countsByYear W43086713212023 @default.
- W4308671321 crossrefType "proceedings-article" @default.
- W4308671321 hasAuthorship W4308671321A5008056593 @default.
- W4308671321 hasAuthorship W4308671321A5013881064 @default.
- W4308671321 hasAuthorship W4308671321A5043301109 @default.
- W4308671321 hasAuthorship W4308671321A5044455276 @default.
- W4308671321 hasBestOaLocation W43086713211 @default.
- W4308671321 hasConcept C119857082 @default.
- W4308671321 hasConcept C124101348 @default.
- W4308671321 hasConcept C132525143 @default.
- W4308671321 hasConcept C13280743 @default.
- W4308671321 hasConcept C146849305 @default.
- W4308671321 hasConcept C154945302 @default.
- W4308671321 hasConcept C185798385 @default.
- W4308671321 hasConcept C205649164 @default.
- W4308671321 hasConcept C2776145971 @default.
- W4308671321 hasConcept C41008148 @default.
- W4308671321 hasConcept C67186912 @default.
- W4308671321 hasConcept C77088390 @default.
- W4308671321 hasConcept C8038995 @default.
- W4308671321 hasConcept C80444323 @default.
- W4308671321 hasConceptScore W4308671321C119857082 @default.
- W4308671321 hasConceptScore W4308671321C124101348 @default.
- W4308671321 hasConceptScore W4308671321C132525143 @default.
- W4308671321 hasConceptScore W4308671321C13280743 @default.
- W4308671321 hasConceptScore W4308671321C146849305 @default.
- W4308671321 hasConceptScore W4308671321C154945302 @default.
- W4308671321 hasConceptScore W4308671321C185798385 @default.
- W4308671321 hasConceptScore W4308671321C205649164 @default.
- W4308671321 hasConceptScore W4308671321C2776145971 @default.
- W4308671321 hasConceptScore W4308671321C41008148 @default.
- W4308671321 hasConceptScore W4308671321C67186912 @default.
- W4308671321 hasConceptScore W4308671321C77088390 @default.
- W4308671321 hasConceptScore W4308671321C8038995 @default.
- W4308671321 hasConceptScore W4308671321C80444323 @default.
- W4308671321 hasLocation W43086713211 @default.
- W4308671321 hasLocation W43086713212 @default.
- W4308671321 hasOpenAccess W4308671321 @default.
- W4308671321 hasPrimaryLocation W43086713211 @default.
- W4308671321 hasRelatedWork W3007915134 @default.
- W4308671321 hasRelatedWork W3046775127 @default.
- W4308671321 hasRelatedWork W3123344745 @default.
- W4308671321 hasRelatedWork W3196155444 @default.
- W4308671321 hasRelatedWork W3208099188 @default.
- W4308671321 hasRelatedWork W3209574120 @default.
- W4308671321 hasRelatedWork W3212493609 @default.
- W4308671321 hasRelatedWork W4285260836 @default.
- W4308671321 hasRelatedWork W4306321456 @default.
- W4308671321 hasRelatedWork W4367692580 @default.
- W4308671321 isParatext "false" @default.
- W4308671321 isRetracted "false" @default.
- W4308671321 workType "article" @default.