Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380993150> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4380993150 abstract "Graph neural networks have shown impressive capabilities in solving various graph learning tasks, particularly excelling in node classification. However, their effectiveness can be hindered by the challenges arising from the widespread existence of noisy measurements associated with the topological or nodal information present in real-world graphs. These inaccuracies in observations can corrupt the crucial patterns within the graph data, ultimately resulting in undesirable performance in practical applications. To address these issues, this paper proposes a novel uncertainty-aware graph learning framework motivated by distributionally robust optimization. Specifically, we use a graph neural network-based encoder to embed the node features and find the optimal node embeddings by minimizing the worst-case risk through a minimax formulation. Such an uncertainty-aware learning process leads to improved node representations and a more robust graph predictive model that effectively mitigates the impact of uncertainty arising from data noise. Our experimental result shows that the proposed framework achieves superior predictive performance compared to the state-of-the-art baselines under various noisy settings." @default.
- W4380993150 created "2023-06-17" @default.
- W4380993150 creator A5003888491 @default.
- W4380993150 creator A5044455276 @default.
- W4380993150 creator A5074367596 @default.
- W4380993150 date "2023-06-13" @default.
- W4380993150 modified "2023-09-25" @default.
- W4380993150 title "Uncertainty-Aware Robust Learning on Noisy Graphs" @default.
- W4380993150 doi "https://doi.org/10.48550/arxiv.2306.08210" @default.
- W4380993150 hasPublicationYear "2023" @default.
- W4380993150 type Work @default.
- W4380993150 citedByCount "0" @default.
- W4380993150 crossrefType "posted-content" @default.
- W4380993150 hasAuthorship W4380993150A5003888491 @default.
- W4380993150 hasAuthorship W4380993150A5044455276 @default.
- W4380993150 hasAuthorship W4380993150A5074367596 @default.
- W4380993150 hasBestOaLocation W43809931501 @default.
- W4380993150 hasConcept C111919701 @default.
- W4380993150 hasConcept C118505674 @default.
- W4380993150 hasConcept C119857082 @default.
- W4380993150 hasConcept C126255220 @default.
- W4380993150 hasConcept C127413603 @default.
- W4380993150 hasConcept C132525143 @default.
- W4380993150 hasConcept C149728462 @default.
- W4380993150 hasConcept C154945302 @default.
- W4380993150 hasConcept C33923547 @default.
- W4380993150 hasConcept C41008148 @default.
- W4380993150 hasConcept C62611344 @default.
- W4380993150 hasConcept C66938386 @default.
- W4380993150 hasConcept C80444323 @default.
- W4380993150 hasConceptScore W4380993150C111919701 @default.
- W4380993150 hasConceptScore W4380993150C118505674 @default.
- W4380993150 hasConceptScore W4380993150C119857082 @default.
- W4380993150 hasConceptScore W4380993150C126255220 @default.
- W4380993150 hasConceptScore W4380993150C127413603 @default.
- W4380993150 hasConceptScore W4380993150C132525143 @default.
- W4380993150 hasConceptScore W4380993150C149728462 @default.
- W4380993150 hasConceptScore W4380993150C154945302 @default.
- W4380993150 hasConceptScore W4380993150C33923547 @default.
- W4380993150 hasConceptScore W4380993150C41008148 @default.
- W4380993150 hasConceptScore W4380993150C62611344 @default.
- W4380993150 hasConceptScore W4380993150C66938386 @default.
- W4380993150 hasConceptScore W4380993150C80444323 @default.
- W4380993150 hasLocation W43809931501 @default.
- W4380993150 hasOpenAccess W4380993150 @default.
- W4380993150 hasPrimaryLocation W43809931501 @default.
- W4380993150 hasRelatedWork W2275988210 @default.
- W4380993150 hasRelatedWork W2356875448 @default.
- W4380993150 hasRelatedWork W2385621972 @default.
- W4380993150 hasRelatedWork W2946121727 @default.
- W4380993150 hasRelatedWork W2961085424 @default.
- W4380993150 hasRelatedWork W3196755225 @default.
- W4380993150 hasRelatedWork W4288347894 @default.
- W4380993150 hasRelatedWork W4306674287 @default.
- W4380993150 hasRelatedWork W4323323198 @default.
- W4380993150 hasRelatedWork W4224009465 @default.
- W4380993150 isParatext "false" @default.
- W4380993150 isRetracted "false" @default.
- W4380993150 workType "article" @default.