Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319431310> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4319431310 abstract "Negative samples are usually used in previous contrastive learning methods, but such methods often have major defects in graph contrastive learning. In the knowledge graph, the potential relationship between nodes is mainly represented by the edge relationship between nodes. However, in the previous contrastive learning method, the distance between positive and negative samples is infinitely expanded, so this potential relationship is destroyed. Therefore, inspired by the state-of-the-art contrastive learning methods without negative examples, we propose a None-Negative Graph Contrastive Learning method (NGCL) for generalized zero-shot learning. NGCL uses the dropout graph augmentation method to make a graph node have its corresponding positive sample, and the two augmentation graphs are compared with positive samples after graph convolution and MLP. Experimental results on real-world datasets without predefined attributes demonstrate the effectiveness of our method." @default.
- W4319431310 created "2023-02-09" @default.
- W4319431310 creator A5015318204 @default.
- W4319431310 creator A5051270776 @default.
- W4319431310 creator A5080737029 @default.
- W4319431310 date "2022-10-01" @default.
- W4319431310 modified "2023-10-16" @default.
- W4319431310 title "None-Negative Graph Contrastive Learning for Knowledge-Driven Zero-Shot Learning" @default.
- W4319431310 cites W2601051138 @default.
- W4319431310 cites W2611632661 @default.
- W4319431310 cites W2736590139 @default.
- W4319431310 cites W2746797088 @default.
- W4319431310 cites W2798991696 @default.
- W4319431310 cites W2963486920 @default.
- W4319431310 cites W2979300990 @default.
- W4319431310 cites W2979579363 @default.
- W4319431310 cites W3035524453 @default.
- W4319431310 cites W3108655343 @default.
- W4319431310 cites W3153385943 @default.
- W4319431310 cites W3171007011 @default.
- W4319431310 cites W3173292968 @default.
- W4319431310 cites W3208016583 @default.
- W4319431310 doi "https://doi.org/10.1109/icebe55470.2022.00027" @default.
- W4319431310 hasPublicationYear "2022" @default.
- W4319431310 type Work @default.
- W4319431310 citedByCount "0" @default.
- W4319431310 crossrefType "proceedings-article" @default.
- W4319431310 hasAuthorship W4319431310A5015318204 @default.
- W4319431310 hasAuthorship W4319431310A5051270776 @default.
- W4319431310 hasAuthorship W4319431310A5080737029 @default.
- W4319431310 hasConcept C132525143 @default.
- W4319431310 hasConcept C154945302 @default.
- W4319431310 hasConcept C33923547 @default.
- W4319431310 hasConcept C41008148 @default.
- W4319431310 hasConcept C80444323 @default.
- W4319431310 hasConceptScore W4319431310C132525143 @default.
- W4319431310 hasConceptScore W4319431310C154945302 @default.
- W4319431310 hasConceptScore W4319431310C33923547 @default.
- W4319431310 hasConceptScore W4319431310C41008148 @default.
- W4319431310 hasConceptScore W4319431310C80444323 @default.
- W4319431310 hasFunder F4320321001 @default.
- W4319431310 hasLocation W43194313101 @default.
- W4319431310 hasOpenAccess W4319431310 @default.
- W4319431310 hasPrimaryLocation W43194313101 @default.
- W4319431310 hasRelatedWork W1986393357 @default.
- W4319431310 hasRelatedWork W2023331372 @default.
- W4319431310 hasRelatedWork W2107367999 @default.
- W4319431310 hasRelatedWork W2110866863 @default.
- W4319431310 hasRelatedWork W2391817034 @default.
- W4319431310 hasRelatedWork W2559087450 @default.
- W4319431310 hasRelatedWork W2754997651 @default.
- W4319431310 hasRelatedWork W3107474891 @default.
- W4319431310 hasRelatedWork W4229769709 @default.
- W4319431310 hasRelatedWork W4317655900 @default.
- W4319431310 isParatext "false" @default.
- W4319431310 isRetracted "false" @default.
- W4319431310 workType "article" @default.