Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361194118> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4361194118 abstract "Graph augmentations are essential for graph contrastive learning. Most existing works use pre-defined random augmentations, which are usually unable to adapt to different input graphs and fail to consider the impact of different nodes and edges on graph semantics. To address this issue, we propose a framework called Hybrid Augmented Automated Graph Contrastive Learning (HAGCL). HAGCL consists of a feature-level learnable view generator and an edge-level learnable view generator. The view generators are end-to-end differentiable to learn the probability distribution of views conditioned on the input graph. It insures to learn the most semantically meaningful structure in terms of features and topology, respectively. Furthermore, we propose an improved joint training strategy, which can achieve better results than previous works without resorting to any weak label information in the downstream tasks and extensive evaluation of additional work." @default.
- W4361194118 created "2023-03-31" @default.
- W4361194118 creator A5018389659 @default.
- W4361194118 creator A5033080900 @default.
- W4361194118 creator A5082314947 @default.
- W4361194118 date "2023-03-23" @default.
- W4361194118 modified "2023-10-18" @default.
- W4361194118 title "Hybrid Augmented Automated Graph Contrastive Learning" @default.
- W4361194118 doi "https://doi.org/10.48550/arxiv.2303.15182" @default.
- W4361194118 hasPublicationYear "2023" @default.
- W4361194118 type Work @default.
- W4361194118 citedByCount "0" @default.
- W4361194118 crossrefType "posted-content" @default.
- W4361194118 hasAuthorship W4361194118A5018389659 @default.
- W4361194118 hasAuthorship W4361194118A5033080900 @default.
- W4361194118 hasAuthorship W4361194118A5082314947 @default.
- W4361194118 hasBestOaLocation W43611941181 @default.
- W4361194118 hasConcept C105795698 @default.
- W4361194118 hasConcept C121332964 @default.
- W4361194118 hasConcept C132525143 @default.
- W4361194118 hasConcept C154945302 @default.
- W4361194118 hasConcept C163258240 @default.
- W4361194118 hasConcept C18653775 @default.
- W4361194118 hasConcept C204321447 @default.
- W4361194118 hasConcept C2780992000 @default.
- W4361194118 hasConcept C33923547 @default.
- W4361194118 hasConcept C41008148 @default.
- W4361194118 hasConcept C62520636 @default.
- W4361194118 hasConcept C80444323 @default.
- W4361194118 hasConceptScore W4361194118C105795698 @default.
- W4361194118 hasConceptScore W4361194118C121332964 @default.
- W4361194118 hasConceptScore W4361194118C132525143 @default.
- W4361194118 hasConceptScore W4361194118C154945302 @default.
- W4361194118 hasConceptScore W4361194118C163258240 @default.
- W4361194118 hasConceptScore W4361194118C18653775 @default.
- W4361194118 hasConceptScore W4361194118C204321447 @default.
- W4361194118 hasConceptScore W4361194118C2780992000 @default.
- W4361194118 hasConceptScore W4361194118C33923547 @default.
- W4361194118 hasConceptScore W4361194118C41008148 @default.
- W4361194118 hasConceptScore W4361194118C62520636 @default.
- W4361194118 hasConceptScore W4361194118C80444323 @default.
- W4361194118 hasLocation W43611941181 @default.
- W4361194118 hasOpenAccess W4361194118 @default.
- W4361194118 hasPrimaryLocation W43611941181 @default.
- W4361194118 hasRelatedWork W1552159754 @default.
- W4361194118 hasRelatedWork W2000422883 @default.
- W4361194118 hasRelatedWork W2148757832 @default.
- W4361194118 hasRelatedWork W2293457016 @default.
- W4361194118 hasRelatedWork W2368651715 @default.
- W4361194118 hasRelatedWork W2390459957 @default.
- W4361194118 hasRelatedWork W2611614995 @default.
- W4361194118 hasRelatedWork W2789919619 @default.
- W4361194118 hasRelatedWork W3107474891 @default.
- W4361194118 hasRelatedWork W4321496520 @default.
- W4361194118 isParatext "false" @default.
- W4361194118 isRetracted "false" @default.
- W4361194118 workType "article" @default.