Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176943960> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3176943960 endingPage "25" @default.
- W3176943960 startingPage "1" @default.
- W3176943960 abstract "Graph neural networks (GNNs) are important tools for transductive learning tasks, such as node classification in graphs, due to their expressive power in capturing complex interdependency between nodes. To enable graph neural network learning, existing works typically assume that labeled nodes, from two or multiple classes, are provided, so that a discriminative classifier can be learned from the labeled data. In reality, this assumption might be too restrictive for applications, as users may only provide labels of interest in a single class for a small number of nodes. In addition, most GNN models only aggregate information from short distances (e.g., 1-hop neighbors) in each round, and fail to capture long distance relationship in graphs. In this paper, we propose a novel graph neural network framework, long-short distance aggregation networks (LSDAN), to overcome these limitations. By generating multiple graphs at different distance levels, based on the adjacency matrix, we develop a long-short distance attention model to model these graphs. The direct neighbors are captured via a short-distance attention mechanism, and neighbors with long distance are captured by a long distance attention mechanism. Two novel risk estimators are further employed to aggregate long-short-distance networks, for PU learning and the loss is back-propagated for model learning. Experimental results on real-world datasets demonstrate the effectiveness of our algorithm." @default.
- W3176943960 created "2021-07-05" @default.
- W3176943960 creator A5008056593 @default.
- W3176943960 creator A5021845515 @default.
- W3176943960 creator A5026669797 @default.
- W3176943960 creator A5084641325 @default.
- W3176943960 date "2021-06-28" @default.
- W3176943960 modified "2023-09-30" @default.
- W3176943960 title "Learning Graph Neural Networks with Positive and Unlabeled Nodes" @default.
- W3176943960 cites W2016210016 @default.
- W3176943960 cites W2116341502 @default.
- W3176943960 cites W2132870739 @default.
- W3176943960 cites W2194775991 @default.
- W3176943960 cites W2323770312 @default.
- W3176943960 cites W2393319904 @default.
- W3176943960 cites W2768914708 @default.
- W3176943960 cites W2788338934 @default.
- W3176943960 cites W2962756421 @default.
- W3176943960 cites W2963791934 @default.
- W3176943960 cites W2972209102 @default.
- W3176943960 cites W2984580262 @default.
- W3176943960 cites W3003874400 @default.
- W3176943960 cites W3012644407 @default.
- W3176943960 cites W3104097132 @default.
- W3176943960 cites W3105705953 @default.
- W3176943960 cites W4210257598 @default.
- W3176943960 doi "https://doi.org/10.1145/3450316" @default.
- W3176943960 hasPublicationYear "2021" @default.
- W3176943960 type Work @default.
- W3176943960 sameAs 3176943960 @default.
- W3176943960 citedByCount "14" @default.
- W3176943960 countsByYear W31769439602021 @default.
- W3176943960 countsByYear W31769439602022 @default.
- W3176943960 countsByYear W31769439602023 @default.
- W3176943960 crossrefType "journal-article" @default.
- W3176943960 hasAuthorship W3176943960A5008056593 @default.
- W3176943960 hasAuthorship W3176943960A5021845515 @default.
- W3176943960 hasAuthorship W3176943960A5026669797 @default.
- W3176943960 hasAuthorship W3176943960A5084641325 @default.
- W3176943960 hasBestOaLocation W31769439602 @default.
- W3176943960 hasConcept C111208986 @default.
- W3176943960 hasConcept C11413529 @default.
- W3176943960 hasConcept C114614502 @default.
- W3176943960 hasConcept C119857082 @default.
- W3176943960 hasConcept C124101348 @default.
- W3176943960 hasConcept C132525143 @default.
- W3176943960 hasConcept C154945302 @default.
- W3176943960 hasConcept C180356752 @default.
- W3176943960 hasConcept C33923547 @default.
- W3176943960 hasConcept C41008148 @default.
- W3176943960 hasConcept C50644808 @default.
- W3176943960 hasConcept C5349765 @default.
- W3176943960 hasConcept C80444323 @default.
- W3176943960 hasConcept C97931131 @default.
- W3176943960 hasConceptScore W3176943960C111208986 @default.
- W3176943960 hasConceptScore W3176943960C11413529 @default.
- W3176943960 hasConceptScore W3176943960C114614502 @default.
- W3176943960 hasConceptScore W3176943960C119857082 @default.
- W3176943960 hasConceptScore W3176943960C124101348 @default.
- W3176943960 hasConceptScore W3176943960C132525143 @default.
- W3176943960 hasConceptScore W3176943960C154945302 @default.
- W3176943960 hasConceptScore W3176943960C180356752 @default.
- W3176943960 hasConceptScore W3176943960C33923547 @default.
- W3176943960 hasConceptScore W3176943960C41008148 @default.
- W3176943960 hasConceptScore W3176943960C50644808 @default.
- W3176943960 hasConceptScore W3176943960C5349765 @default.
- W3176943960 hasConceptScore W3176943960C80444323 @default.
- W3176943960 hasConceptScore W3176943960C97931131 @default.
- W3176943960 hasFunder F4320306076 @default.
- W3176943960 hasIssue "6" @default.
- W3176943960 hasLocation W31769439601 @default.
- W3176943960 hasLocation W31769439602 @default.
- W3176943960 hasOpenAccess W3176943960 @default.
- W3176943960 hasPrimaryLocation W31769439601 @default.
- W3176943960 hasRelatedWork W1974398340 @default.
- W3176943960 hasRelatedWork W2022179729 @default.
- W3176943960 hasRelatedWork W2037357970 @default.
- W3176943960 hasRelatedWork W2165035860 @default.
- W3176943960 hasRelatedWork W2737156094 @default.
- W3176943960 hasRelatedWork W2887753156 @default.
- W3176943960 hasRelatedWork W3135467434 @default.
- W3176943960 hasRelatedWork W3164306936 @default.
- W3176943960 hasRelatedWork W37364050 @default.
- W3176943960 hasRelatedWork W4295883551 @default.
- W3176943960 hasVolume "15" @default.
- W3176943960 isParatext "false" @default.
- W3176943960 isRetracted "false" @default.
- W3176943960 magId "3176943960" @default.
- W3176943960 workType "article" @default.