Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327532556> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4327532556 abstract "Link prediction between two nodes is a critical task in graph machine learning. Most approaches are based on variants of graph neural networks (GNNs) that focus on transductive link prediction and have high inference latency. However, many real-world applications require fast inference over new nodes in inductive settings where no information on connectivity is available for these nodes. Thereby, node features provide an inevitable alternative in the latter scenario. To that end, we propose Graph2Feat, which enables inductive link prediction by exploiting knowledge distillation (KD) through the Student-Teacher learning framework. In particular, Graph2Feat learns to match the representations of a lightweight student multi-layer perceptron (MLP) with a more expressive teacher GNN while learning to predict missing links based on the node features, thus attaining both GNN’s expressiveness and MLP’s fast inference. Furthermore, our approach is general; it is suitable for transductive and inductive link predictions on different types of graphs regardless of them being homogeneous or heterogeneous, directed or undirected. We carry out extensive experiments on seven real-world datasets including homogeneous and heterogeneous graphs. Our experiments demonstrate that Graph2Feat significantly outperforms SOTA methods in terms of AUC and average precision in homogeneous and heterogeneous graphs. Finally, Graph2Feat has the minimum inference time compared to the SOTA methods, and 100x acceleration compared to GNNs. The code and datasets are available on GitHub1." @default.
- W4327532556 created "2023-03-17" @default.
- W4327532556 creator A5036955634 @default.
- W4327532556 creator A5041411651 @default.
- W4327532556 creator A5081446545 @default.
- W4327532556 date "2023-04-30" @default.
- W4327532556 modified "2023-10-14" @default.
- W4327532556 title "Graph2Feat: Inductive Link Prediction via Knowledge Distillation" @default.
- W4327532556 cites W2743104969 @default.
- W4327532556 cites W3003579202 @default.
- W4327532556 cites W3104097132 @default.
- W4327532556 cites W3160872503 @default.
- W4327532556 cites W4284704639 @default.
- W4327532556 cites W4312998847 @default.
- W4327532556 doi "https://doi.org/10.1145/3543873.3587596" @default.
- W4327532556 hasPublicationYear "2023" @default.
- W4327532556 type Work @default.
- W4327532556 citedByCount "0" @default.
- W4327532556 crossrefType "proceedings-article" @default.
- W4327532556 hasAuthorship W4327532556A5036955634 @default.
- W4327532556 hasAuthorship W4327532556A5041411651 @default.
- W4327532556 hasAuthorship W4327532556A5081446545 @default.
- W4327532556 hasBestOaLocation W43275325561 @default.
- W4327532556 hasConcept C114614502 @default.
- W4327532556 hasConcept C119857082 @default.
- W4327532556 hasConcept C127413603 @default.
- W4327532556 hasConcept C132525143 @default.
- W4327532556 hasConcept C154945302 @default.
- W4327532556 hasConcept C179717631 @default.
- W4327532556 hasConcept C2776214188 @default.
- W4327532556 hasConcept C2778753846 @default.
- W4327532556 hasConcept C31258907 @default.
- W4327532556 hasConcept C33923547 @default.
- W4327532556 hasConcept C41008148 @default.
- W4327532556 hasConcept C50644808 @default.
- W4327532556 hasConcept C60908668 @default.
- W4327532556 hasConcept C62611344 @default.
- W4327532556 hasConcept C66882249 @default.
- W4327532556 hasConcept C66938386 @default.
- W4327532556 hasConcept C80444323 @default.
- W4327532556 hasConceptScore W4327532556C114614502 @default.
- W4327532556 hasConceptScore W4327532556C119857082 @default.
- W4327532556 hasConceptScore W4327532556C127413603 @default.
- W4327532556 hasConceptScore W4327532556C132525143 @default.
- W4327532556 hasConceptScore W4327532556C154945302 @default.
- W4327532556 hasConceptScore W4327532556C179717631 @default.
- W4327532556 hasConceptScore W4327532556C2776214188 @default.
- W4327532556 hasConceptScore W4327532556C2778753846 @default.
- W4327532556 hasConceptScore W4327532556C31258907 @default.
- W4327532556 hasConceptScore W4327532556C33923547 @default.
- W4327532556 hasConceptScore W4327532556C41008148 @default.
- W4327532556 hasConceptScore W4327532556C50644808 @default.
- W4327532556 hasConceptScore W4327532556C60908668 @default.
- W4327532556 hasConceptScore W4327532556C62611344 @default.
- W4327532556 hasConceptScore W4327532556C66882249 @default.
- W4327532556 hasConceptScore W4327532556C66938386 @default.
- W4327532556 hasConceptScore W4327532556C80444323 @default.
- W4327532556 hasFunder F4320320217 @default.
- W4327532556 hasLocation W43275325561 @default.
- W4327532556 hasLocation W43275325562 @default.
- W4327532556 hasOpenAccess W4327532556 @default.
- W4327532556 hasPrimaryLocation W43275325561 @default.
- W4327532556 hasRelatedWork W2292855655 @default.
- W4327532556 hasRelatedWork W3185179407 @default.
- W4327532556 hasRelatedWork W4200196661 @default.
- W4327532556 hasRelatedWork W4206558754 @default.
- W4327532556 hasRelatedWork W4220975826 @default.
- W4327532556 hasRelatedWork W4231994957 @default.
- W4327532556 hasRelatedWork W4233002550 @default.
- W4327532556 hasRelatedWork W4280611221 @default.
- W4327532556 hasRelatedWork W4285741730 @default.
- W4327532556 hasRelatedWork W4316082230 @default.
- W4327532556 isParatext "false" @default.
- W4327532556 isRetracted "false" @default.
- W4327532556 workType "article" @default.