Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383175621> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4383175621 abstract "Recent efforts in fake news detection have witnessed a surge of interest in using graph neural networks (GNNs) to exploit rich social context. Existing studies generally leverage fixed graph structures, assuming that the graphs accurately represent the related social engagements. However, edge noise remains a critical challenge in real-world graphs, as training on suboptimal structures can severely limit the expressiveness of GNNs. Despite initial efforts in graph structure learning (GSL), prior works often leverage node features to update edge weights, resulting in heavy computational costs that hinder the methods' applicability to large-scale social graphs. In this work, we approach the fake news detection problem with a novel aspect of social graph refinement. We find that the degrees of news article nodes exhibit distinctive patterns, which are indicative of news veracity. Guided by this, we propose DECOR, a novel application of Degree-Corrected Stochastic Blockmodels to the fake news detection problem. Specifically, we encapsulate our empirical observations into a lightweight social graph refinement component that iteratively updates the edge weights via a learnable degree correction mask, which allows for joint optimization with a GNN-based detector. Extensive experiments on two real-world benchmarks validate the effectiveness and efficiency of DECOR1." @default.
- W4383175621 created "2023-07-05" @default.
- W4383175621 creator A5003613490 @default.
- W4383175621 creator A5065675832 @default.
- W4383175621 date "2023-08-04" @default.
- W4383175621 modified "2023-10-07" @default.
- W4383175621 title "DECOR: Degree-Corrected Social Graph Refinement for Fake News Detection" @default.
- W4383175621 cites W2075585362 @default.
- W4383175621 cites W2410465342 @default.
- W4383175621 cites W2803831897 @default.
- W4383175621 cites W2898550644 @default.
- W4383175621 cites W2903981179 @default.
- W4383175621 cites W2906971970 @default.
- W4383175621 cites W2951307134 @default.
- W4383175621 cites W2962972034 @default.
- W4383175621 cites W2979826702 @default.
- W4383175621 cites W2984488829 @default.
- W4383175621 cites W2989424501 @default.
- W4383175621 cites W2994598354 @default.
- W4383175621 cites W3034020579 @default.
- W4383175621 cites W3070920170 @default.
- W4383175621 cites W3081203761 @default.
- W4383175621 cites W3101890897 @default.
- W4383175621 cites W3114204117 @default.
- W4383175621 cites W3156800454 @default.
- W4383175621 cites W3177047401 @default.
- W4383175621 cites W3201124874 @default.
- W4383175621 cites W4212890525 @default.
- W4383175621 cites W4221148143 @default.
- W4383175621 cites W4221168025 @default.
- W4383175621 cites W4224308992 @default.
- W4383175621 cites W4224310546 @default.
- W4383175621 cites W4224313980 @default.
- W4383175621 cites W4224324956 @default.
- W4383175621 cites W4290927845 @default.
- W4383175621 doi "https://doi.org/10.1145/3580305.3599298" @default.
- W4383175621 hasPublicationYear "2023" @default.
- W4383175621 type Work @default.
- W4383175621 citedByCount "0" @default.
- W4383175621 crossrefType "proceedings-article" @default.
- W4383175621 hasAuthorship W4383175621A5003613490 @default.
- W4383175621 hasAuthorship W4383175621A5065675832 @default.
- W4383175621 hasBestOaLocation W43831756211 @default.
- W4383175621 hasConcept C11413529 @default.
- W4383175621 hasConcept C119857082 @default.
- W4383175621 hasConcept C124101348 @default.
- W4383175621 hasConcept C132525143 @default.
- W4383175621 hasConcept C136764020 @default.
- W4383175621 hasConcept C153083717 @default.
- W4383175621 hasConcept C154945302 @default.
- W4383175621 hasConcept C165696696 @default.
- W4383175621 hasConcept C2777522414 @default.
- W4383175621 hasConcept C38652104 @default.
- W4383175621 hasConcept C41008148 @default.
- W4383175621 hasConcept C518677369 @default.
- W4383175621 hasConcept C80444323 @default.
- W4383175621 hasConceptScore W4383175621C11413529 @default.
- W4383175621 hasConceptScore W4383175621C119857082 @default.
- W4383175621 hasConceptScore W4383175621C124101348 @default.
- W4383175621 hasConceptScore W4383175621C132525143 @default.
- W4383175621 hasConceptScore W4383175621C136764020 @default.
- W4383175621 hasConceptScore W4383175621C153083717 @default.
- W4383175621 hasConceptScore W4383175621C154945302 @default.
- W4383175621 hasConceptScore W4383175621C165696696 @default.
- W4383175621 hasConceptScore W4383175621C2777522414 @default.
- W4383175621 hasConceptScore W4383175621C38652104 @default.
- W4383175621 hasConceptScore W4383175621C41008148 @default.
- W4383175621 hasConceptScore W4383175621C518677369 @default.
- W4383175621 hasConceptScore W4383175621C80444323 @default.
- W4383175621 hasLocation W43831756211 @default.
- W4383175621 hasLocation W43831756212 @default.
- W4383175621 hasLocation W43831756213 @default.
- W4383175621 hasOpenAccess W4383175621 @default.
- W4383175621 hasPrimaryLocation W43831756211 @default.
- W4383175621 hasRelatedWork W2135486170 @default.
- W4383175621 hasRelatedWork W2331043530 @default.
- W4383175621 hasRelatedWork W2393933887 @default.
- W4383175621 hasRelatedWork W2748952813 @default.
- W4383175621 hasRelatedWork W2798029542 @default.
- W4383175621 hasRelatedWork W2961085424 @default.
- W4383175621 hasRelatedWork W2997512100 @default.
- W4383175621 hasRelatedWork W3086197249 @default.
- W4383175621 hasRelatedWork W3130812118 @default.
- W4383175621 hasRelatedWork W4297899248 @default.
- W4383175621 isParatext "false" @default.
- W4383175621 isRetracted "false" @default.
- W4383175621 workType "article" @default.