Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367000429> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W4367000429 abstract "Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits their wide use in reality since labels are usually scarce in real applications. Recently, contrastive learning, a self-supervised method, becomes one of the most exciting learning paradigms and shows great potential when there are no labels. In this paper, we study the problem of self-supervised HGNNs and propose a novel co-contrastive learning mechanism for HGNNs, named HeCo. Different from traditional contrastive learning which only focuses on contrasting positive and negative samples, HeCo employs cross-view contrastive mechanism. Specifically, two views of a HIN (network schema and meta-path views) are proposed to learn node embeddings, so as to capture both of local and high-order structures simultaneously. Then the cross-view contrastive learning, as well as a view mask mechanism, is proposed, which is able to extract the positive and negative embeddings from two views. This enables the two views to collaboratively supervise each other and finally learn high-level node embeddings. Moreover, to further boost the performance of HeCo, two additional methods are designed to generate harder negative samples with high quality. Besides the invariant factors, view-specific factors complementally provide the diverse structure information between different nodes, which also should be contained into the final embeddings. Therefore, we need to further explore each view independently and propose a modified model, called HeCo++. Specifically, HeCo++ conducts hierarchical contrastive learning, including cross-view and intra-view contrasts, which aims to enhance the mining of respective structures." @default.
- W4367000429 created "2023-04-27" @default.
- W4367000429 creator A5036881486 @default.
- W4367000429 creator A5051805730 @default.
- W4367000429 creator A5058010200 @default.
- W4367000429 creator A5088229898 @default.
- W4367000429 date "2023-04-24" @default.
- W4367000429 modified "2023-09-26" @default.
- W4367000429 title "Hierarchical Contrastive Learning Enhanced Heterogeneous Graph Neural Network" @default.
- W4367000429 doi "https://doi.org/10.48550/arxiv.2304.12228" @default.
- W4367000429 hasPublicationYear "2023" @default.
- W4367000429 type Work @default.
- W4367000429 citedByCount "0" @default.
- W4367000429 crossrefType "posted-content" @default.
- W4367000429 hasAuthorship W4367000429A5036881486 @default.
- W4367000429 hasAuthorship W4367000429A5051805730 @default.
- W4367000429 hasAuthorship W4367000429A5058010200 @default.
- W4367000429 hasAuthorship W4367000429A5088229898 @default.
- W4367000429 hasBestOaLocation W43670004291 @default.
- W4367000429 hasConcept C119857082 @default.
- W4367000429 hasConcept C132525143 @default.
- W4367000429 hasConcept C154945302 @default.
- W4367000429 hasConcept C41008148 @default.
- W4367000429 hasConcept C50644808 @default.
- W4367000429 hasConcept C52146309 @default.
- W4367000429 hasConcept C80444323 @default.
- W4367000429 hasConceptScore W4367000429C119857082 @default.
- W4367000429 hasConceptScore W4367000429C132525143 @default.
- W4367000429 hasConceptScore W4367000429C154945302 @default.
- W4367000429 hasConceptScore W4367000429C41008148 @default.
- W4367000429 hasConceptScore W4367000429C50644808 @default.
- W4367000429 hasConceptScore W4367000429C52146309 @default.
- W4367000429 hasConceptScore W4367000429C80444323 @default.
- W4367000429 hasLocation W43670004291 @default.
- W4367000429 hasOpenAccess W4367000429 @default.
- W4367000429 hasPrimaryLocation W43670004291 @default.
- W4367000429 hasRelatedWork W2386387936 @default.
- W4367000429 hasRelatedWork W2961085424 @default.
- W4367000429 hasRelatedWork W3046775127 @default.
- W4367000429 hasRelatedWork W4205958290 @default.
- W4367000429 hasRelatedWork W4285260836 @default.
- W4367000429 hasRelatedWork W4286629047 @default.
- W4367000429 hasRelatedWork W4306321456 @default.
- W4367000429 hasRelatedWork W4306674287 @default.
- W4367000429 hasRelatedWork W1629725936 @default.
- W4367000429 hasRelatedWork W4224009465 @default.
- W4367000429 isParatext "false" @default.
- W4367000429 isRetracted "false" @default.
- W4367000429 workType "article" @default.