Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387148002> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4387148002 abstract "Graph Neural Networks (GNNs) have garnered considerable interest due to their exceptional performance in a wide range of graph machine learning tasks. Nevertheless, the majority of GNN-based approaches have been examined using well-annotated benchmark datasets, leading to suboptimal performance in real-world graph learning scenarios. To bridge this gap, the present paper investigates the problem of graph transfer learning in the presence of label noise, which transfers knowledge from a noisy source graph to an unlabeled target graph. We introduce a novel technique termed Balance Alignment and Information-aware Examination (ALEX) to address this challenge. ALEX first employs singular value decomposition to generate different views with crucial structural semantics, which help provide robust node representations using graph contrastive learning. To mitigate both label shift and domain shift, we estimate a prior distribution to build subgraphs with balanced label distributions. Building on this foundation, an adversarial domain discriminator is incorporated for the implicit domain alignment of complex multi-modal distributions. Furthermore, we project node representations into a different space, optimizing the mutual information between the projected features and labels. Subsequently, the inconsistency of similarity structures is evaluated to identify noisy samples with potential overfitting. Comprehensive experiments on various benchmark datasets substantiate the outstanding superiority of the proposed ALEX in different settings." @default.
- W4387148002 created "2023-09-29" @default.
- W4387148002 creator A5018666299 @default.
- W4387148002 creator A5020600355 @default.
- W4387148002 creator A5054462908 @default.
- W4387148002 creator A5058440014 @default.
- W4387148002 creator A5073859117 @default.
- W4387148002 creator A5080733133 @default.
- W4387148002 date "2023-09-26" @default.
- W4387148002 modified "2023-10-18" @default.
- W4387148002 title "ALEX: Towards Effective Graph Transfer Learning with Noisy Labels" @default.
- W4387148002 doi "https://doi.org/10.48550/arxiv.2309.14673" @default.
- W4387148002 hasPublicationYear "2023" @default.
- W4387148002 type Work @default.
- W4387148002 citedByCount "0" @default.
- W4387148002 crossrefType "posted-content" @default.
- W4387148002 hasAuthorship W4387148002A5018666299 @default.
- W4387148002 hasAuthorship W4387148002A5020600355 @default.
- W4387148002 hasAuthorship W4387148002A5054462908 @default.
- W4387148002 hasAuthorship W4387148002A5058440014 @default.
- W4387148002 hasAuthorship W4387148002A5073859117 @default.
- W4387148002 hasAuthorship W4387148002A5080733133 @default.
- W4387148002 hasBestOaLocation W43871480021 @default.
- W4387148002 hasConcept C108583219 @default.
- W4387148002 hasConcept C119857082 @default.
- W4387148002 hasConcept C132525143 @default.
- W4387148002 hasConcept C150899416 @default.
- W4387148002 hasConcept C154945302 @default.
- W4387148002 hasConcept C41008148 @default.
- W4387148002 hasConcept C80444323 @default.
- W4387148002 hasConceptScore W4387148002C108583219 @default.
- W4387148002 hasConceptScore W4387148002C119857082 @default.
- W4387148002 hasConceptScore W4387148002C132525143 @default.
- W4387148002 hasConceptScore W4387148002C150899416 @default.
- W4387148002 hasConceptScore W4387148002C154945302 @default.
- W4387148002 hasConceptScore W4387148002C41008148 @default.
- W4387148002 hasConceptScore W4387148002C80444323 @default.
- W4387148002 hasLocation W43871480021 @default.
- W4387148002 hasOpenAccess W4387148002 @default.
- W4387148002 hasPrimaryLocation W43871480021 @default.
- W4387148002 hasRelatedWork W2889705046 @default.
- W4387148002 hasRelatedWork W2960456850 @default.
- W4387148002 hasRelatedWork W3192840557 @default.
- W4387148002 hasRelatedWork W4223943233 @default.
- W4387148002 hasRelatedWork W4312200629 @default.
- W4387148002 hasRelatedWork W4317565044 @default.
- W4387148002 hasRelatedWork W4360585206 @default.
- W4387148002 hasRelatedWork W4380075502 @default.
- W4387148002 hasRelatedWork W4382286161 @default.
- W4387148002 hasRelatedWork W4386213806 @default.
- W4387148002 isParatext "false" @default.
- W4387148002 isRetracted "false" @default.
- W4387148002 workType "article" @default.