Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224320982> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4224320982 abstract "The self-supervised graph representation learning has achieved much success in recent web based research and applications, such as recommendation system, social networks, and anomaly detection. However, existing works suffer from two problems. Firstly, in social networks, the influential neighbors are important, but the overwhelming routine in graph representation-learning utilizes the node-wise similarity metric defined on embedding vectors that cannot exactly capture the subtle local structure and the network proximity. Secondly, existing works implicitly assume a universal distribution across datasets, which presumably leads to sub-optimal models considering the potential distribution shift. To address these problems, in this paper, we learn structural embeddings in which the proximity is characterized by 1-Wasserstein distance. We propose a distributionally robust self-supervised graph neural network framework to learn the representations. More specifically, in our method, the embeddings are computed based on subgraphs centering at the node of interest and represent both the node of interest and its neighbors, which better preserves the local structure of nodes. To make our model end-to-end trainable, we adopt a deep implicit layer to compute the Wasserstein distance, which can be formulated as a differentiable convex optimization problem. Meanwhile, our distributionally robust formulation explicitly constrains the maximal diversity for matched queries and keys. As such, our model is insensitive to the data distributions and has better generalization abilities. Extensive experiments demonstrate that the graph encoder learned by our approach can be utilized for various downstream analyses, including node classification, graph classification, and top-k similarity search. The results show our algorithm outperforms state-of-the-art baselines, and the ablation study validates the effectiveness of our design." @default.
- W4224320982 created "2022-04-26" @default.
- W4224320982 creator A5014924409 @default.
- W4224320982 creator A5025781094 @default.
- W4224320982 creator A5060016795 @default.
- W4224320982 creator A5062247330 @default.
- W4224320982 date "2022-04-25" @default.
- W4224320982 modified "2023-09-25" @default.
- W4224320982 title "Robust Self-Supervised Structural Graph Neural Network for Social Network Prediction" @default.
- W4224320982 cites W1996174542 @default.
- W4224320982 cites W2008857988 @default.
- W4224320982 cites W2021948263 @default.
- W4224320982 cites W2057685268 @default.
- W4224320982 cites W2090891622 @default.
- W4224320982 cites W2133299088 @default.
- W4224320982 cites W2156020699 @default.
- W4224320982 cites W2250844151 @default.
- W4224320982 cites W2432978112 @default.
- W4224320982 cites W2788919350 @default.
- W4224320982 cites W2792234394 @default.
- W4224320982 cites W2798991696 @default.
- W4224320982 cites W2808000122 @default.
- W4224320982 cites W2952205826 @default.
- W4224320982 cites W2963718112 @default.
- W4224320982 cites W2966694634 @default.
- W4224320982 cites W3035524453 @default.
- W4224320982 cites W3095746859 @default.
- W4224320982 cites W3099152386 @default.
- W4224320982 cites W3100848837 @default.
- W4224320982 cites W3104097132 @default.
- W4224320982 cites W3105705953 @default.
- W4224320982 cites W3152616003 @default.
- W4224320982 cites W3152663991 @default.
- W4224320982 cites W3153361501 @default.
- W4224320982 cites W3153663296 @default.
- W4224320982 cites W3154000428 @default.
- W4224320982 cites W3154091824 @default.
- W4224320982 cites W3155496675 @default.
- W4224320982 cites W3156861396 @default.
- W4224320982 cites W3169450514 @default.
- W4224320982 doi "https://doi.org/10.1145/3485447.3512182" @default.
- W4224320982 hasPublicationYear "2022" @default.
- W4224320982 type Work @default.
- W4224320982 citedByCount "4" @default.
- W4224320982 countsByYear W42243209822022 @default.
- W4224320982 countsByYear W42243209822023 @default.
- W4224320982 crossrefType "proceedings-article" @default.
- W4224320982 hasAuthorship W4224320982A5014924409 @default.
- W4224320982 hasAuthorship W4224320982A5025781094 @default.
- W4224320982 hasAuthorship W4224320982A5060016795 @default.
- W4224320982 hasAuthorship W4224320982A5062247330 @default.
- W4224320982 hasConcept C127413603 @default.
- W4224320982 hasConcept C132525143 @default.
- W4224320982 hasConcept C134306372 @default.
- W4224320982 hasConcept C154945302 @default.
- W4224320982 hasConcept C177148314 @default.
- W4224320982 hasConcept C33923547 @default.
- W4224320982 hasConcept C41008148 @default.
- W4224320982 hasConcept C41608201 @default.
- W4224320982 hasConcept C62611344 @default.
- W4224320982 hasConcept C66938386 @default.
- W4224320982 hasConcept C75564084 @default.
- W4224320982 hasConcept C80444323 @default.
- W4224320982 hasConceptScore W4224320982C127413603 @default.
- W4224320982 hasConceptScore W4224320982C132525143 @default.
- W4224320982 hasConceptScore W4224320982C134306372 @default.
- W4224320982 hasConceptScore W4224320982C154945302 @default.
- W4224320982 hasConceptScore W4224320982C177148314 @default.
- W4224320982 hasConceptScore W4224320982C33923547 @default.
- W4224320982 hasConceptScore W4224320982C41008148 @default.
- W4224320982 hasConceptScore W4224320982C41608201 @default.
- W4224320982 hasConceptScore W4224320982C62611344 @default.
- W4224320982 hasConceptScore W4224320982C66938386 @default.
- W4224320982 hasConceptScore W4224320982C75564084 @default.
- W4224320982 hasConceptScore W4224320982C80444323 @default.
- W4224320982 hasFunder F4320306076 @default.
- W4224320982 hasLocation W42243209821 @default.
- W4224320982 hasOpenAccess W4224320982 @default.
- W4224320982 hasPrimaryLocation W42243209821 @default.
- W4224320982 hasRelatedWork W2893186803 @default.
- W4224320982 hasRelatedWork W2923818335 @default.
- W4224320982 hasRelatedWork W3035116611 @default.
- W4224320982 hasRelatedWork W3044354590 @default.
- W4224320982 hasRelatedWork W3094605108 @default.
- W4224320982 hasRelatedWork W4212923699 @default.
- W4224320982 hasRelatedWork W4226361842 @default.
- W4224320982 hasRelatedWork W4284975088 @default.
- W4224320982 hasRelatedWork W4287763734 @default.
- W4224320982 hasRelatedWork W4310879833 @default.
- W4224320982 isParatext "false" @default.
- W4224320982 isRetracted "false" @default.
- W4224320982 workType "article" @default.