Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308732418> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4308732418 endingPage "23" @default.
- W4308732418 startingPage "1" @default.
- W4308732418 abstract "Self-supervised graph-level representation learning has recently received considerable attention. Given varied input distributions, jointly learning graphs’ unique and common features is vital to downstream tasks. Inspired by graph contrastive learning (GCL), which targets maximizing the agreement between graph representations from different views, we propose an Ada ptive self-supervised framework, Ada-MIP, considering both M utual I nformation between views (unique features) and inter-graph P roximity (common features). Specifically, Ada-MIP learns graphs’ unique information through a learnable and probably injective augmenter, which can acquire more adaptive views compared to the augmentation strategies applied by existing GCL methods; to learn graphs’ common information, we employ graph kernels to calculate graphs’ proximity and learn graph representations among which the precomputed proximity is preserved. By sharing a global encoder, graphs’ unique and common information can be well integrated into the graph representations learned by Ada-MIP. Ada-MIP is also extendable to semi-supervised scenarios, with our experiments confirming its superior performance in both unsupervised and semi-supervised tasks." @default.
- W4308732418 created "2022-11-15" @default.
- W4308732418 creator A5010856777 @default.
- W4308732418 creator A5034483183 @default.
- W4308732418 creator A5048486573 @default.
- W4308732418 creator A5051539538 @default.
- W4308732418 creator A5065537354 @default.
- W4308732418 creator A5068607867 @default.
- W4308732418 creator A5078547624 @default.
- W4308732418 creator A5086413877 @default.
- W4308732418 creator A5088059599 @default.
- W4308732418 date "2023-04-07" @default.
- W4308732418 modified "2023-10-16" @default.
- W4308732418 title "Ada-MIP: Adaptive Self-supervised Graph Representation Learning via Mutual Information and Proximity Optimization" @default.
- W4308732418 cites W1816257748 @default.
- W4308732418 cites W1988115241 @default.
- W4308732418 cites W2080635178 @default.
- W4308732418 cites W2122925692 @default.
- W4308732418 cites W2147286743 @default.
- W4308732418 cites W2153635508 @default.
- W4308732418 cites W2181072414 @default.
- W4308732418 cites W2604795503 @default.
- W4308732418 cites W2808803559 @default.
- W4308732418 cites W2962756421 @default.
- W4308732418 cites W2999044305 @default.
- W4308732418 cites W3012816161 @default.
- W4308732418 cites W3095746859 @default.
- W4308732418 cites W3101073376 @default.
- W4308732418 cites W4206482253 @default.
- W4308732418 cites W4221023051 @default.
- W4308732418 doi "https://doi.org/10.1145/3568165" @default.
- W4308732418 hasPublicationYear "2023" @default.
- W4308732418 type Work @default.
- W4308732418 citedByCount "0" @default.
- W4308732418 crossrefType "journal-article" @default.
- W4308732418 hasAuthorship W4308732418A5010856777 @default.
- W4308732418 hasAuthorship W4308732418A5034483183 @default.
- W4308732418 hasAuthorship W4308732418A5048486573 @default.
- W4308732418 hasAuthorship W4308732418A5051539538 @default.
- W4308732418 hasAuthorship W4308732418A5065537354 @default.
- W4308732418 hasAuthorship W4308732418A5068607867 @default.
- W4308732418 hasAuthorship W4308732418A5078547624 @default.
- W4308732418 hasAuthorship W4308732418A5086413877 @default.
- W4308732418 hasAuthorship W4308732418A5088059599 @default.
- W4308732418 hasConcept C111919701 @default.
- W4308732418 hasConcept C118505674 @default.
- W4308732418 hasConcept C119857082 @default.
- W4308732418 hasConcept C132525143 @default.
- W4308732418 hasConcept C152139883 @default.
- W4308732418 hasConcept C154945302 @default.
- W4308732418 hasConcept C41008148 @default.
- W4308732418 hasConcept C59404180 @default.
- W4308732418 hasConcept C80444323 @default.
- W4308732418 hasConceptScore W4308732418C111919701 @default.
- W4308732418 hasConceptScore W4308732418C118505674 @default.
- W4308732418 hasConceptScore W4308732418C119857082 @default.
- W4308732418 hasConceptScore W4308732418C132525143 @default.
- W4308732418 hasConceptScore W4308732418C152139883 @default.
- W4308732418 hasConceptScore W4308732418C154945302 @default.
- W4308732418 hasConceptScore W4308732418C41008148 @default.
- W4308732418 hasConceptScore W4308732418C59404180 @default.
- W4308732418 hasConceptScore W4308732418C80444323 @default.
- W4308732418 hasIssue "5" @default.
- W4308732418 hasLocation W43087324181 @default.
- W4308732418 hasOpenAccess W4308732418 @default.
- W4308732418 hasPrimaryLocation W43087324181 @default.
- W4308732418 hasRelatedWork W2891961174 @default.
- W4308732418 hasRelatedWork W2908875379 @default.
- W4308732418 hasRelatedWork W2946121727 @default.
- W4308732418 hasRelatedWork W2972984751 @default.
- W4308732418 hasRelatedWork W3087493185 @default.
- W4308732418 hasRelatedWork W3158586592 @default.
- W4308732418 hasRelatedWork W4206762304 @default.
- W4308732418 hasRelatedWork W4213225422 @default.
- W4308732418 hasRelatedWork W4221136938 @default.
- W4308732418 hasRelatedWork W4288347894 @default.
- W4308732418 hasVolume "17" @default.
- W4308732418 isParatext "false" @default.
- W4308732418 isRetracted "false" @default.
- W4308732418 workType "article" @default.