Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287197019> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4287197019 abstract "Graph neural networks (GNN) have been ubiquitous in graph node classification tasks. Most of GNN methods update the node embedding iteratively by aggregating its neighbors' information. However, they often suffer from negative disturbance, due to edges connecting nodes with different labels. One approach to alleviate this negative disturbance is to use attention to learn the weights of aggregation, but current attention-based GNNs only consider feature similarity and also suffer from the lack of supervision. In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention. The hard attention is learned on labels for a refined graph structure with fewer inter-class edges, so that the aggregation's negative disturbance can be reduced. The soft attention aims to learn the aggregation weights based on features over the refined graph structure to enhance information gains during message passing. Particularly, we formulate our model under the EM framework, and the learned attention is used to guide the label propagation in the M-step and the feature propagation in the E-step, respectively. Extensive experiments are performed on six well-known benchmark graph datasets to verify the effectiveness of the proposed method." @default.
- W4287197019 created "2022-07-25" @default.
- W4287197019 creator A5010479652 @default.
- W4287197019 creator A5011405813 @default.
- W4287197019 creator A5015817857 @default.
- W4287197019 creator A5036309463 @default.
- W4287197019 creator A5047175539 @default.
- W4287197019 creator A5081238418 @default.
- W4287197019 date "2021-04-28" @default.
- W4287197019 modified "2023-09-30" @default.
- W4287197019 title "Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification" @default.
- W4287197019 doi "https://doi.org/10.48550/arxiv.2104.13718" @default.
- W4287197019 hasPublicationYear "2021" @default.
- W4287197019 type Work @default.
- W4287197019 citedByCount "0" @default.
- W4287197019 crossrefType "posted-content" @default.
- W4287197019 hasAuthorship W4287197019A5010479652 @default.
- W4287197019 hasAuthorship W4287197019A5011405813 @default.
- W4287197019 hasAuthorship W4287197019A5015817857 @default.
- W4287197019 hasAuthorship W4287197019A5036309463 @default.
- W4287197019 hasAuthorship W4287197019A5047175539 @default.
- W4287197019 hasAuthorship W4287197019A5081238418 @default.
- W4287197019 hasBestOaLocation W42871970191 @default.
- W4287197019 hasConcept C119857082 @default.
- W4287197019 hasConcept C124101348 @default.
- W4287197019 hasConcept C132525143 @default.
- W4287197019 hasConcept C153180895 @default.
- W4287197019 hasConcept C154945302 @default.
- W4287197019 hasConcept C41008148 @default.
- W4287197019 hasConcept C41608201 @default.
- W4287197019 hasConcept C75564084 @default.
- W4287197019 hasConcept C80444323 @default.
- W4287197019 hasConcept C98763669 @default.
- W4287197019 hasConceptScore W4287197019C119857082 @default.
- W4287197019 hasConceptScore W4287197019C124101348 @default.
- W4287197019 hasConceptScore W4287197019C132525143 @default.
- W4287197019 hasConceptScore W4287197019C153180895 @default.
- W4287197019 hasConceptScore W4287197019C154945302 @default.
- W4287197019 hasConceptScore W4287197019C41008148 @default.
- W4287197019 hasConceptScore W4287197019C41608201 @default.
- W4287197019 hasConceptScore W4287197019C75564084 @default.
- W4287197019 hasConceptScore W4287197019C80444323 @default.
- W4287197019 hasConceptScore W4287197019C98763669 @default.
- W4287197019 hasLocation W42871970191 @default.
- W4287197019 hasOpenAccess W4287197019 @default.
- W4287197019 hasPrimaryLocation W42871970191 @default.
- W4287197019 hasRelatedWork W11189869 @default.
- W4287197019 hasRelatedWork W11594795 @default.
- W4287197019 hasRelatedWork W11644230 @default.
- W4287197019 hasRelatedWork W12712126 @default.
- W4287197019 hasRelatedWork W5374421 @default.
- W4287197019 hasRelatedWork W5684657 @default.
- W4287197019 hasRelatedWork W7585623 @default.
- W4287197019 hasRelatedWork W7842670 @default.
- W4287197019 hasRelatedWork W9035903 @default.
- W4287197019 hasRelatedWork W9043603 @default.
- W4287197019 isParatext "false" @default.
- W4287197019 isRetracted "false" @default.
- W4287197019 workType "article" @default.