Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323914306> ?p ?o ?g. }
- W4323914306 endingPage "785" @default.
- W4323914306 startingPage "772" @default.
- W4323914306 abstract "Semi-supervised node classification with Graph Convolutional Network (GCN) is an attractive topic in social media analysis and applications. Recent studies show that GCN-based classification methods can facilitate the accuracy increase of learning algorithms. However, most of the existing methods do not conduct adequate explorations of the complementary information within the topology structure. Besides, they also suffer from the insufficient excavation of useful information among nodes and the scarcity of labeled samples, resulting in undesired classification performance. To cope with these issues, this paper proposes a contrastive GCN-based framework to jointly leverage the topology graph and the self-adaptive topology graph with feature information in semi-supervised information. In order to extract more valid potential information in the topology graph and increase the flexibility of the framework, we learn an adjacency matrix supervised by a flexible loss that exploits node embeddings to reinforce the topological representation capability of the adjacency matrix. To maximize the homogeneity of these two distinct graphs, we design an improved semi-supervised contrastive loss. In order to enrich scarce label information, we propose a self-supervised mechanism to generate reliable pseudo labels from abundant unlabeled data, which further refines the learnable adjacency matrix. With these modules, both unlabeled and labeled samples jointly furnish the supervision signals, thereby improving the accuracy of the proposed model. Extensive experimental results on real-world datasets demonstrate the effectiveness and superiority of the proposed algorithm against state-of-the-arts." @default.
- W4323914306 created "2023-03-12" @default.
- W4323914306 creator A5002405830 @default.
- W4323914306 creator A5068046629 @default.
- W4323914306 creator A5073666526 @default.
- W4323914306 creator A5084849129 @default.
- W4323914306 date "2023-01-01" @default.
- W4323914306 modified "2023-10-17" @default.
- W4323914306 title "Contrastive Graph Convolutional Networks With Generative Adjacency Matrix" @default.
- W4323914306 cites W2011295372 @default.
- W4323914306 cites W2015245929 @default.
- W4323914306 cites W2138621090 @default.
- W4323914306 cites W2393319904 @default.
- W4323914306 cites W2808867307 @default.
- W4323914306 cites W2808987817 @default.
- W4323914306 cites W2963066159 @default.
- W4323914306 cites W2963084622 @default.
- W4323914306 cites W2964051675 @default.
- W4323914306 cites W2965744772 @default.
- W4323914306 cites W2979969178 @default.
- W4323914306 cites W2998269939 @default.
- W4323914306 cites W3008273026 @default.
- W4323914306 cites W3019023591 @default.
- W4323914306 cites W3026900506 @default.
- W4323914306 cites W3035524453 @default.
- W4323914306 cites W3035541121 @default.
- W4323914306 cites W3100993589 @default.
- W4323914306 cites W3108496296 @default.
- W4323914306 cites W3127947687 @default.
- W4323914306 cites W3128443161 @default.
- W4323914306 cites W3158166861 @default.
- W4323914306 cites W3173109190 @default.
- W4323914306 cites W3173292968 @default.
- W4323914306 cites W3173365306 @default.
- W4323914306 cites W3174905206 @default.
- W4323914306 cites W3180838358 @default.
- W4323914306 cites W3182710365 @default.
- W4323914306 cites W3195106575 @default.
- W4323914306 cites W3197341760 @default.
- W4323914306 cites W4221150350 @default.
- W4323914306 cites W4226022916 @default.
- W4323914306 cites W4304140736 @default.
- W4323914306 doi "https://doi.org/10.1109/tsp.2023.3254888" @default.
- W4323914306 hasPublicationYear "2023" @default.
- W4323914306 type Work @default.
- W4323914306 citedByCount "2" @default.
- W4323914306 countsByYear W43239143062023 @default.
- W4323914306 crossrefType "journal-article" @default.
- W4323914306 hasAuthorship W4323914306A5002405830 @default.
- W4323914306 hasAuthorship W4323914306A5068046629 @default.
- W4323914306 hasAuthorship W4323914306A5073666526 @default.
- W4323914306 hasAuthorship W4323914306A5084849129 @default.
- W4323914306 hasConcept C103275481 @default.
- W4323914306 hasConcept C110484373 @default.
- W4323914306 hasConcept C111919701 @default.
- W4323914306 hasConcept C11413529 @default.
- W4323914306 hasConcept C114614502 @default.
- W4323914306 hasConcept C119857082 @default.
- W4323914306 hasConcept C132525143 @default.
- W4323914306 hasConcept C154945302 @default.
- W4323914306 hasConcept C178790620 @default.
- W4323914306 hasConcept C180356752 @default.
- W4323914306 hasConcept C184720557 @default.
- W4323914306 hasConcept C185592680 @default.
- W4323914306 hasConcept C199845137 @default.
- W4323914306 hasConcept C2781311116 @default.
- W4323914306 hasConcept C33923547 @default.
- W4323914306 hasConcept C41008148 @default.
- W4323914306 hasConcept C80444323 @default.
- W4323914306 hasConceptScore W4323914306C103275481 @default.
- W4323914306 hasConceptScore W4323914306C110484373 @default.
- W4323914306 hasConceptScore W4323914306C111919701 @default.
- W4323914306 hasConceptScore W4323914306C11413529 @default.
- W4323914306 hasConceptScore W4323914306C114614502 @default.
- W4323914306 hasConceptScore W4323914306C119857082 @default.
- W4323914306 hasConceptScore W4323914306C132525143 @default.
- W4323914306 hasConceptScore W4323914306C154945302 @default.
- W4323914306 hasConceptScore W4323914306C178790620 @default.
- W4323914306 hasConceptScore W4323914306C180356752 @default.
- W4323914306 hasConceptScore W4323914306C184720557 @default.
- W4323914306 hasConceptScore W4323914306C185592680 @default.
- W4323914306 hasConceptScore W4323914306C199845137 @default.
- W4323914306 hasConceptScore W4323914306C2781311116 @default.
- W4323914306 hasConceptScore W4323914306C33923547 @default.
- W4323914306 hasConceptScore W4323914306C41008148 @default.
- W4323914306 hasConceptScore W4323914306C80444323 @default.
- W4323914306 hasFunder F4320321001 @default.
- W4323914306 hasLocation W43239143061 @default.
- W4323914306 hasOpenAccess W4323914306 @default.
- W4323914306 hasPrimaryLocation W43239143061 @default.
- W4323914306 hasRelatedWork W1967590974 @default.
- W4323914306 hasRelatedWork W1997448565 @default.
- W4323914306 hasRelatedWork W2059430635 @default.
- W4323914306 hasRelatedWork W2090509666 @default.
- W4323914306 hasRelatedWork W2160456903 @default.
- W4323914306 hasRelatedWork W2350423711 @default.
- W4323914306 hasRelatedWork W2603288023 @default.
- W4323914306 hasRelatedWork W2604585036 @default.