Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310376439> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4310376439 endingPage "24" @default.
- W4310376439 startingPage "1" @default.
- W4310376439 abstract "For many years, within the information network analysis and mining (INAM) area, heterogeneous information network (HIN) is considered as a hot topic which have attracted attentions from many researchers. In fact, HIN is considered as the sufficient reflection of real-world information networks which contains multiple types of nodes and links (e.g., knowledge graph, social networks, etc.). Within HIN-based analysis and mining domain, meta-path is considered as the key concept which is employed to extract rich contextual information from semantic relationships, in forms of meta-paths, between multi-typed nodes. However, the various semantic informative sources which are obtained from different meta-paths between nodes are frequently considered as ambiguous and entangled for primitive tasks in INAM area such as node classification, clustering or link prediction. Recently, there are several well-known studies which have dedicated on the disentangling the meta-path-based representations of nodes in HIN through different techniques such as variational embedding and adversarial learning paradigms. However, the disentangled meta-path-based node representation learning in HIN still have several unresolved problems. One of the most crucial limitations of this research direction is related to the capability of properly interpretation for meta-path-varied disentangled node embeddings in order to achieve better fine-tuned performance for different downstream tasks, such as node classification. In order to overcome this problem, in this paper we proposed an improvement of disentangled HIN representation learning for node classification task with the employment of attention-based mechanism, called as: HAttDE model. A self-attention-based mechanism is placed between the encoding and generating components in order to softly align and interpret multiple fused meta-path-based node representations into better classification-friendly embedding spaces. Extensive experiments in benchmark networked datasets demonstrated the effectiveness of our proposed model in comparing with recent state-of-the-art HIN embedding baselines." @default.
- W4310376439 created "2022-12-10" @default.
- W4310376439 creator A5078988974 @default.
- W4310376439 date "2022-11-30" @default.
- W4310376439 modified "2023-10-17" @default.
- W4310376439 title "An Attention-Based Adversarial Disentangle Heterogeneous Embedding for Improving Node Classification" @default.
- W4310376439 cites W2393319904 @default.
- W4310376439 cites W2911286998 @default.
- W4310376439 cites W2945266622 @default.
- W4310376439 cites W2952343887 @default.
- W4310376439 cites W2962756421 @default.
- W4310376439 cites W2963707260 @default.
- W4310376439 cites W2963919031 @default.
- W4310376439 cites W2965857891 @default.
- W4310376439 cites W2998324911 @default.
- W4310376439 cites W3012871709 @default.
- W4310376439 cites W3105705953 @default.
- W4310376439 cites W3108202858 @default.
- W4310376439 cites W3114303065 @default.
- W4310376439 cites W3178951948 @default.
- W4310376439 cites W4206517174 @default.
- W4310376439 cites W4210257598 @default.
- W4310376439 doi "https://doi.org/10.1080/01969722.2022.2151172" @default.
- W4310376439 hasPublicationYear "2022" @default.
- W4310376439 type Work @default.
- W4310376439 citedByCount "1" @default.
- W4310376439 countsByYear W43103764392023 @default.
- W4310376439 crossrefType "journal-article" @default.
- W4310376439 hasAuthorship W4310376439A5078988974 @default.
- W4310376439 hasConcept C119857082 @default.
- W4310376439 hasConcept C124101348 @default.
- W4310376439 hasConcept C127413603 @default.
- W4310376439 hasConcept C132525143 @default.
- W4310376439 hasConcept C154945302 @default.
- W4310376439 hasConcept C17744445 @default.
- W4310376439 hasConcept C199539241 @default.
- W4310376439 hasConcept C26517878 @default.
- W4310376439 hasConcept C2776359362 @default.
- W4310376439 hasConcept C2777735758 @default.
- W4310376439 hasConcept C2778753846 @default.
- W4310376439 hasConcept C31258907 @default.
- W4310376439 hasConcept C37736160 @default.
- W4310376439 hasConcept C38652104 @default.
- W4310376439 hasConcept C41008148 @default.
- W4310376439 hasConcept C41608201 @default.
- W4310376439 hasConcept C59404180 @default.
- W4310376439 hasConcept C62611344 @default.
- W4310376439 hasConcept C66938386 @default.
- W4310376439 hasConcept C73555534 @default.
- W4310376439 hasConcept C75564084 @default.
- W4310376439 hasConcept C80444323 @default.
- W4310376439 hasConcept C94625758 @default.
- W4310376439 hasConceptScore W4310376439C119857082 @default.
- W4310376439 hasConceptScore W4310376439C124101348 @default.
- W4310376439 hasConceptScore W4310376439C127413603 @default.
- W4310376439 hasConceptScore W4310376439C132525143 @default.
- W4310376439 hasConceptScore W4310376439C154945302 @default.
- W4310376439 hasConceptScore W4310376439C17744445 @default.
- W4310376439 hasConceptScore W4310376439C199539241 @default.
- W4310376439 hasConceptScore W4310376439C26517878 @default.
- W4310376439 hasConceptScore W4310376439C2776359362 @default.
- W4310376439 hasConceptScore W4310376439C2777735758 @default.
- W4310376439 hasConceptScore W4310376439C2778753846 @default.
- W4310376439 hasConceptScore W4310376439C31258907 @default.
- W4310376439 hasConceptScore W4310376439C37736160 @default.
- W4310376439 hasConceptScore W4310376439C38652104 @default.
- W4310376439 hasConceptScore W4310376439C41008148 @default.
- W4310376439 hasConceptScore W4310376439C41608201 @default.
- W4310376439 hasConceptScore W4310376439C59404180 @default.
- W4310376439 hasConceptScore W4310376439C62611344 @default.
- W4310376439 hasConceptScore W4310376439C66938386 @default.
- W4310376439 hasConceptScore W4310376439C73555534 @default.
- W4310376439 hasConceptScore W4310376439C75564084 @default.
- W4310376439 hasConceptScore W4310376439C80444323 @default.
- W4310376439 hasConceptScore W4310376439C94625758 @default.
- W4310376439 hasLocation W43103764391 @default.
- W4310376439 hasOpenAccess W4310376439 @default.
- W4310376439 hasPrimaryLocation W43103764391 @default.
- W4310376439 hasRelatedWork W2953770707 @default.
- W4310376439 hasRelatedWork W3035116611 @default.
- W4310376439 hasRelatedWork W3103545790 @default.
- W4310376439 hasRelatedWork W3149439221 @default.
- W4310376439 hasRelatedWork W4206939502 @default.
- W4310376439 hasRelatedWork W4221140418 @default.
- W4310376439 hasRelatedWork W4287763734 @default.
- W4310376439 hasRelatedWork W4302283439 @default.
- W4310376439 hasRelatedWork W4310879833 @default.
- W4310376439 hasRelatedWork W4323323198 @default.
- W4310376439 isParatext "false" @default.
- W4310376439 isRetracted "false" @default.
- W4310376439 workType "article" @default.