Matches in SemOpenAlex for { <https://semopenalex.org/work/W4212890525> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4212890525 abstract "Graph Neural Networks (GNNs) have shown their great ability in modeling graph structured data. However, real-world graphs usually contain structure noises and have limited labeled nodes. The performance of GNNs would drop significantly when trained on such graphs, which hinders the adoption of GNNs on many applications. Thus, it is important to develop noise-resistant GNNs with limited labeled nodes. However, the work on this is rather limited. Therefore, we study a novel problem of developing robust GNNs on noisy graphs with limited labeled nodes. Our analysis shows that both the noisy edges and limited labeled nodes could harm the message-passing mechanism of GNNs. To mitigate these issues, we propose a novel framework which adopts the noisy edges as supervision to learn a denoised and dense graph, which can down-weight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes. The generated edges are further used to regularize the predictions of unlabeled nodes with label smoothness to better train GNNs. Experimental results on real-world datasets demonstrate the robustness of the proposed framework on noisy graphs with limited labeled nodes." @default.
- W4212890525 created "2022-02-24" @default.
- W4212890525 creator A5011048500 @default.
- W4212890525 creator A5044301848 @default.
- W4212890525 creator A5077970328 @default.
- W4212890525 creator A5091395218 @default.
- W4212890525 date "2022-02-11" @default.
- W4212890525 modified "2023-10-16" @default.
- W4212890525 title "Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels" @default.
- W4212890525 cites W2099352187 @default.
- W4212890525 cites W2162630660 @default.
- W4212890525 cites W2803831897 @default.
- W4212890525 cites W2890187992 @default.
- W4212890525 cites W2932399282 @default.
- W4212890525 cites W2945827377 @default.
- W4212890525 cites W2948729509 @default.
- W4212890525 cites W2963084622 @default.
- W4212890525 cites W2963911286 @default.
- W4212890525 cites W2994598354 @default.
- W4212890525 cites W2998122931 @default.
- W4212890525 cites W2999817249 @default.
- W4212890525 cites W3081203761 @default.
- W4212890525 cites W3117178429 @default.
- W4212890525 cites W3125182500 @default.
- W4212890525 cites W3136543599 @default.
- W4212890525 cites W3136640655 @default.
- W4212890525 cites W3166215705 @default.
- W4212890525 cites W3207981989 @default.
- W4212890525 doi "https://doi.org/10.1145/3488560.3498408" @default.
- W4212890525 hasPublicationYear "2022" @default.
- W4212890525 type Work @default.
- W4212890525 citedByCount "16" @default.
- W4212890525 countsByYear W42128905252022 @default.
- W4212890525 countsByYear W42128905252023 @default.
- W4212890525 crossrefType "proceedings-article" @default.
- W4212890525 hasAuthorship W4212890525A5011048500 @default.
- W4212890525 hasAuthorship W4212890525A5044301848 @default.
- W4212890525 hasAuthorship W4212890525A5077970328 @default.
- W4212890525 hasAuthorship W4212890525A5091395218 @default.
- W4212890525 hasBestOaLocation W42128905252 @default.
- W4212890525 hasConcept C104317684 @default.
- W4212890525 hasConcept C119857082 @default.
- W4212890525 hasConcept C120314980 @default.
- W4212890525 hasConcept C132525143 @default.
- W4212890525 hasConcept C154945302 @default.
- W4212890525 hasConcept C185592680 @default.
- W4212890525 hasConcept C2984842247 @default.
- W4212890525 hasConcept C41008148 @default.
- W4212890525 hasConcept C50644808 @default.
- W4212890525 hasConcept C55493867 @default.
- W4212890525 hasConcept C63479239 @default.
- W4212890525 hasConcept C80444323 @default.
- W4212890525 hasConcept C854659 @default.
- W4212890525 hasConceptScore W4212890525C104317684 @default.
- W4212890525 hasConceptScore W4212890525C119857082 @default.
- W4212890525 hasConceptScore W4212890525C120314980 @default.
- W4212890525 hasConceptScore W4212890525C132525143 @default.
- W4212890525 hasConceptScore W4212890525C154945302 @default.
- W4212890525 hasConceptScore W4212890525C185592680 @default.
- W4212890525 hasConceptScore W4212890525C2984842247 @default.
- W4212890525 hasConceptScore W4212890525C41008148 @default.
- W4212890525 hasConceptScore W4212890525C50644808 @default.
- W4212890525 hasConceptScore W4212890525C55493867 @default.
- W4212890525 hasConceptScore W4212890525C63479239 @default.
- W4212890525 hasConceptScore W4212890525C80444323 @default.
- W4212890525 hasConceptScore W4212890525C854659 @default.
- W4212890525 hasFunder F4320306076 @default.
- W4212890525 hasFunder F4320338281 @default.
- W4212890525 hasLocation W42128905251 @default.
- W4212890525 hasLocation W42128905252 @default.
- W4212890525 hasOpenAccess W4212890525 @default.
- W4212890525 hasPrimaryLocation W42128905251 @default.
- W4212890525 hasRelatedWork W1834449470 @default.
- W4212890525 hasRelatedWork W2281761054 @default.
- W4212890525 hasRelatedWork W2368564840 @default.
- W4212890525 hasRelatedWork W2961085424 @default.
- W4212890525 hasRelatedWork W2962182036 @default.
- W4212890525 hasRelatedWork W2965198885 @default.
- W4212890525 hasRelatedWork W3036535673 @default.
- W4212890525 hasRelatedWork W3170944957 @default.
- W4212890525 hasRelatedWork W4288102844 @default.
- W4212890525 hasRelatedWork W4311734044 @default.
- W4212890525 isParatext "false" @default.
- W4212890525 isRetracted "false" @default.
- W4212890525 workType "article" @default.