Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360764501> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4360764501 abstract "Real-world link prediction problems often deal with data from multiple domains, where data may be highly skewed and imbalanced. Computer vision research has studied similar issues under the Few-Shot Learning (FSL) umbrella. However, this problem has rarely been addressed and explored in the graph domain, specifically for link prediction. In this work, we propose an adversarial training-based framework that aims at improving link prediction for highly skewed and imbalanced graphs from different domains by generating domain agnostic embedding. We introduce a domain discriminator on pairs of graph-level embedding. We then use the discriminator to improve the model in an adversarial way, such that the graph embedding generated by the model are domain agnostic. We test our ideas on one large real-world user-business-review dataset and three benchmark datasets. Our results demonstrate that when domain differences exist, our method creates better graph embedding that are more evenly distributed across domains and generate better prediction outcomes. In the absence of domain differences, our method is on par with state-of-the-art." @default.
- W4360764501 created "2023-03-25" @default.
- W4360764501 creator A5008531526 @default.
- W4360764501 creator A5017698170 @default.
- W4360764501 creator A5038736812 @default.
- W4360764501 creator A5048817284 @default.
- W4360764501 creator A5085251345 @default.
- W4360764501 creator A5086529957 @default.
- W4360764501 date "2022-12-01" @default.
- W4360764501 modified "2023-10-17" @default.
- W4360764501 title "Few-Shot Link Prediction with Domain-Agnostic Graph Embedding" @default.
- W4360764501 cites W2115733720 @default.
- W4360764501 cites W2963169753 @default.
- W4360764501 cites W2963241486 @default.
- W4360764501 cites W2963943197 @default.
- W4360764501 cites W3035286001 @default.
- W4360764501 cites W3136640655 @default.
- W4360764501 doi "https://doi.org/10.1109/icmla55696.2022.00109" @default.
- W4360764501 hasPublicationYear "2022" @default.
- W4360764501 type Work @default.
- W4360764501 citedByCount "0" @default.
- W4360764501 crossrefType "proceedings-article" @default.
- W4360764501 hasAuthorship W4360764501A5008531526 @default.
- W4360764501 hasAuthorship W4360764501A5017698170 @default.
- W4360764501 hasAuthorship W4360764501A5038736812 @default.
- W4360764501 hasAuthorship W4360764501A5048817284 @default.
- W4360764501 hasAuthorship W4360764501A5085251345 @default.
- W4360764501 hasAuthorship W4360764501A5086529957 @default.
- W4360764501 hasConcept C119857082 @default.
- W4360764501 hasConcept C124101348 @default.
- W4360764501 hasConcept C132525143 @default.
- W4360764501 hasConcept C13280743 @default.
- W4360764501 hasConcept C134306372 @default.
- W4360764501 hasConcept C154945302 @default.
- W4360764501 hasConcept C185798385 @default.
- W4360764501 hasConcept C205649164 @default.
- W4360764501 hasConcept C2778753846 @default.
- W4360764501 hasConcept C2779803651 @default.
- W4360764501 hasConcept C31258907 @default.
- W4360764501 hasConcept C33923547 @default.
- W4360764501 hasConcept C36503486 @default.
- W4360764501 hasConcept C37736160 @default.
- W4360764501 hasConcept C41008148 @default.
- W4360764501 hasConcept C41608201 @default.
- W4360764501 hasConcept C75564084 @default.
- W4360764501 hasConcept C76155785 @default.
- W4360764501 hasConcept C80444323 @default.
- W4360764501 hasConcept C94915269 @default.
- W4360764501 hasConceptScore W4360764501C119857082 @default.
- W4360764501 hasConceptScore W4360764501C124101348 @default.
- W4360764501 hasConceptScore W4360764501C132525143 @default.
- W4360764501 hasConceptScore W4360764501C13280743 @default.
- W4360764501 hasConceptScore W4360764501C134306372 @default.
- W4360764501 hasConceptScore W4360764501C154945302 @default.
- W4360764501 hasConceptScore W4360764501C185798385 @default.
- W4360764501 hasConceptScore W4360764501C205649164 @default.
- W4360764501 hasConceptScore W4360764501C2778753846 @default.
- W4360764501 hasConceptScore W4360764501C2779803651 @default.
- W4360764501 hasConceptScore W4360764501C31258907 @default.
- W4360764501 hasConceptScore W4360764501C33923547 @default.
- W4360764501 hasConceptScore W4360764501C36503486 @default.
- W4360764501 hasConceptScore W4360764501C37736160 @default.
- W4360764501 hasConceptScore W4360764501C41008148 @default.
- W4360764501 hasConceptScore W4360764501C41608201 @default.
- W4360764501 hasConceptScore W4360764501C75564084 @default.
- W4360764501 hasConceptScore W4360764501C76155785 @default.
- W4360764501 hasConceptScore W4360764501C80444323 @default.
- W4360764501 hasConceptScore W4360764501C94915269 @default.
- W4360764501 hasLocation W43607645011 @default.
- W4360764501 hasOpenAccess W4360764501 @default.
- W4360764501 hasPrimaryLocation W43607645011 @default.
- W4360764501 hasRelatedWork W2768762802 @default.
- W4360764501 hasRelatedWork W2932106273 @default.
- W4360764501 hasRelatedWork W2953770707 @default.
- W4360764501 hasRelatedWork W3035116611 @default.
- W4360764501 hasRelatedWork W3047710665 @default.
- W4360764501 hasRelatedWork W3103545790 @default.
- W4360764501 hasRelatedWork W4287763734 @default.
- W4360764501 hasRelatedWork W4288376565 @default.
- W4360764501 hasRelatedWork W4302283439 @default.
- W4360764501 hasRelatedWork W4310879833 @default.
- W4360764501 isParatext "false" @default.
- W4360764501 isRetracted "false" @default.
- W4360764501 workType "article" @default.