Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287748869> ?p ?o ?g. }
Showing items 1 to 50 of
50
with 100 items per page.
- W4287748869 abstract "Graph Neural Networks (GNNs) are versatile, powerful machine learning methods that enable graph structure and feature representation learning, and have applications across many domains. For applications critically requiring interpretation, attention-based GNNs have been leveraged. However, these approaches either rely on specific model architectures or lack a joint consideration of graph structure and node features in their interpretation. Here we present a model-agnostic framework for interpreting important graph structure and node features, Graph neural networks Including SparSe inTerpretability (GISST). With any GNN model, GISST combines an attention mechanism and sparsity regularization to yield an important subgraph and node feature subset related to any graph-based task. Through a single self-attention layer, a GISST model learns an importance probability for each node feature and edge in the input graph. By including these importance probabilities in the model loss function, the probabilities are optimized end-to-end and tied to the task-specific performance. Furthermore, GISST sparsifies these importance probabilities with entropy and L1 regularization to reduce noise in the input graph topology and node features. Our GISST models achieve superior node feature and edge explanation precision in synthetic datasets, as compared to alternative interpretation approaches. Moreover, our GISST models are able to identify important graph structure in real-world datasets. We demonstrate in theory that edge feature importance and multiple edge types can be considered by incorporating them into the GISST edge probability computation. By jointly accounting for topology, node features, and edge features, GISST inherently provides simple and relevant interpretations for any GNN models and tasks." @default.
- W4287748869 created "2022-07-26" @default.
- W4287748869 creator A5029745818 @default.
- W4287748869 creator A5063585604 @default.
- W4287748869 creator A5064098570 @default.
- W4287748869 creator A5073387346 @default.
- W4287748869 creator A5078491431 @default.
- W4287748869 date "2020-06-30" @default.
- W4287748869 modified "2023-09-24" @default.
- W4287748869 title "Graph Neural Networks Including Sparse Interpretability" @default.
- W4287748869 hasPublicationYear "2020" @default.
- W4287748869 type Work @default.
- W4287748869 citedByCount "0" @default.
- W4287748869 crossrefType "posted-content" @default.
- W4287748869 hasAuthorship W4287748869A5029745818 @default.
- W4287748869 hasAuthorship W4287748869A5063585604 @default.
- W4287748869 hasAuthorship W4287748869A5064098570 @default.
- W4287748869 hasAuthorship W4287748869A5073387346 @default.
- W4287748869 hasAuthorship W4287748869A5078491431 @default.
- W4287748869 hasBestOaLocation W42877488691 @default.
- W4287748869 hasConcept C119857082 @default.
- W4287748869 hasConcept C132525143 @default.
- W4287748869 hasConcept C154945302 @default.
- W4287748869 hasConcept C2781067378 @default.
- W4287748869 hasConcept C41008148 @default.
- W4287748869 hasConcept C59404180 @default.
- W4287748869 hasConcept C80444323 @default.
- W4287748869 hasConceptScore W4287748869C119857082 @default.
- W4287748869 hasConceptScore W4287748869C132525143 @default.
- W4287748869 hasConceptScore W4287748869C154945302 @default.
- W4287748869 hasConceptScore W4287748869C2781067378 @default.
- W4287748869 hasConceptScore W4287748869C41008148 @default.
- W4287748869 hasConceptScore W4287748869C59404180 @default.
- W4287748869 hasConceptScore W4287748869C80444323 @default.
- W4287748869 hasLocation W42877488691 @default.
- W4287748869 hasOpenAccess W4287748869 @default.
- W4287748869 hasPrimaryLocation W42877488691 @default.
- W4287748869 hasRelatedWork W10852009 @default.
- W4287748869 hasRelatedWork W11104910 @default.
- W4287748869 hasRelatedWork W11644230 @default.
- W4287748869 hasRelatedWork W12712126 @default.
- W4287748869 hasRelatedWork W14047543 @default.
- W4287748869 hasRelatedWork W2956227 @default.
- W4287748869 hasRelatedWork W7002624 @default.
- W4287748869 hasRelatedWork W7842670 @default.
- W4287748869 hasRelatedWork W8289063 @default.
- W4287748869 hasRelatedWork W9043603 @default.
- W4287748869 isParatext "false" @default.
- W4287748869 isRetracted "false" @default.
- W4287748869 workType "article" @default.