Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366127937> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4366127937 endingPage "357" @default.
- W4366127937 startingPage "343" @default.
- W4366127937 abstract "Graph contrastive learning has become an important approach for learning unsupervised representations of graphs, with the key idea of maximizing the consistency of representations in both augmented views through data augmentation. Existing graph contrastive learning models concentrate on topology enhancement of the graph structure by simply removing/adding edges between nodes randomly, which may not only destroy the important structure of the graph but also generate meaningless graphs, leading to a significant degradation of the contrastive learning performance. In addition, current research is too focused on minimizing losses, while ignoring the intrinsic factors that can affect the quality of node representations, which is detrimental to the training of models and the generation of high-quality node representations. To address these issues, we propose intrinsic augmented graph contrastive learning, named IAG, which consists of two components: 1) In the topology augmentation part, we propose a novel topology augmentation strategy based on potential connections in the feature space, which complements the traditional topology augmentation by allowing different graphs to obtain augmentation strategies more suitable for their own characteristics to advance the traditional graph contrastive learning. 2) We explored the effect of temperature coefficient in the loss function on the quality of the final representation and proposed dynamic temperature with penalty terms, which helps to generate high-quality node representations. Finally, we conducted extensive node classification experiments on 8 real-world datasets. The experimental results show that our proposed method is highly competitive with the existing state-of-the-art baselines and even surpasses some supervised methods." @default.
- W4366127937 created "2023-04-19" @default.
- W4366127937 creator A5000380645 @default.
- W4366127937 creator A5050069346 @default.
- W4366127937 creator A5068470874 @default.
- W4366127937 creator A5087631851 @default.
- W4366127937 date "2023-01-01" @default.
- W4366127937 modified "2023-09-30" @default.
- W4366127937 title "Graph Contrastive Learning with Intrinsic Augmentations" @default.
- W4366127937 cites W2068015060 @default.
- W4366127937 cites W2122925692 @default.
- W4366127937 cites W2155834877 @default.
- W4366127937 cites W2962756421 @default.
- W4366127937 cites W3012816161 @default.
- W4366127937 cites W3095746859 @default.
- W4366127937 cites W3100993589 @default.
- W4366127937 cites W3104097132 @default.
- W4366127937 cites W3175593095 @default.
- W4366127937 cites W4229706427 @default.
- W4366127937 cites W4288278932 @default.
- W4366127937 doi "https://doi.org/10.1007/978-981-99-1549-1_27" @default.
- W4366127937 hasPublicationYear "2023" @default.
- W4366127937 type Work @default.
- W4366127937 citedByCount "0" @default.
- W4366127937 crossrefType "book-chapter" @default.
- W4366127937 hasAuthorship W4366127937A5000380645 @default.
- W4366127937 hasAuthorship W4366127937A5050069346 @default.
- W4366127937 hasAuthorship W4366127937A5068470874 @default.
- W4366127937 hasAuthorship W4366127937A5087631851 @default.
- W4366127937 hasConcept C114614502 @default.
- W4366127937 hasConcept C119857082 @default.
- W4366127937 hasConcept C127413603 @default.
- W4366127937 hasConcept C132525143 @default.
- W4366127937 hasConcept C154945302 @default.
- W4366127937 hasConcept C17744445 @default.
- W4366127937 hasConcept C184720557 @default.
- W4366127937 hasConcept C199539241 @default.
- W4366127937 hasConcept C2776359362 @default.
- W4366127937 hasConcept C2776436953 @default.
- W4366127937 hasConcept C33923547 @default.
- W4366127937 hasConcept C41008148 @default.
- W4366127937 hasConcept C59404180 @default.
- W4366127937 hasConcept C62611344 @default.
- W4366127937 hasConcept C66938386 @default.
- W4366127937 hasConcept C80444323 @default.
- W4366127937 hasConcept C94625758 @default.
- W4366127937 hasConceptScore W4366127937C114614502 @default.
- W4366127937 hasConceptScore W4366127937C119857082 @default.
- W4366127937 hasConceptScore W4366127937C127413603 @default.
- W4366127937 hasConceptScore W4366127937C132525143 @default.
- W4366127937 hasConceptScore W4366127937C154945302 @default.
- W4366127937 hasConceptScore W4366127937C17744445 @default.
- W4366127937 hasConceptScore W4366127937C184720557 @default.
- W4366127937 hasConceptScore W4366127937C199539241 @default.
- W4366127937 hasConceptScore W4366127937C2776359362 @default.
- W4366127937 hasConceptScore W4366127937C2776436953 @default.
- W4366127937 hasConceptScore W4366127937C33923547 @default.
- W4366127937 hasConceptScore W4366127937C41008148 @default.
- W4366127937 hasConceptScore W4366127937C59404180 @default.
- W4366127937 hasConceptScore W4366127937C62611344 @default.
- W4366127937 hasConceptScore W4366127937C66938386 @default.
- W4366127937 hasConceptScore W4366127937C80444323 @default.
- W4366127937 hasConceptScore W4366127937C94625758 @default.
- W4366127937 hasLocation W43661279371 @default.
- W4366127937 hasOpenAccess W4366127937 @default.
- W4366127937 hasPrimaryLocation W43661279371 @default.
- W4366127937 hasRelatedWork W2366655048 @default.
- W4366127937 hasRelatedWork W2728391469 @default.
- W4366127937 hasRelatedWork W2891961174 @default.
- W4366127937 hasRelatedWork W2908875379 @default.
- W4366127937 hasRelatedWork W3001496086 @default.
- W4366127937 hasRelatedWork W3087493185 @default.
- W4366127937 hasRelatedWork W3158586592 @default.
- W4366127937 hasRelatedWork W4206762304 @default.
- W4366127937 hasRelatedWork W4221136938 @default.
- W4366127937 hasRelatedWork W4320165504 @default.
- W4366127937 isParatext "false" @default.
- W4366127937 isRetracted "false" @default.
- W4366127937 workType "book-chapter" @default.