Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386896750> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4386896750 abstract "As special information carriers containing both structure and feature information, graphs are widely used in graph mining, e.g., Graph Neural Networks (GNNs). However, graph data are stored separately in multiple distributed parties in some practical scenarios, which may not be directly shared due to conflicts of interest. Hence, federated graph neural networks are proposed to address such data silo issues while preserving each party’s privacy (or client). Nevertheless, different graph data distributions of various parties, which is known as the statistical heterogeneity, may degrade the performance of naive federated learning algorithms like FedAvg. In this paper, we propose FedEgo, a federated graph learning framework based on ego-graphs to tackle the challenges above, in which each client will train their local models while also contributing to the training of a global model. FedEgo applies GraphSAGE over ego-graphs to make full use of the structure information and utilizes Mixup for privacy concerns. To deal with the statistical heterogeneity, we integrate personalization into learning and propose an adaptive mixing coefficient strategy that enables clients to achieve their optimal personalization. Extensive experimental results and in-depth analysis demonstrate the effectiveness of FedEgo." @default.
- W4386896750 created "2023-09-21" @default.
- W4386896750 creator A5000582109 @default.
- W4386896750 creator A5028890544 @default.
- W4386896750 creator A5041581408 @default.
- W4386896750 creator A5069084441 @default.
- W4386896750 creator A5075696732 @default.
- W4386896750 creator A5084807160 @default.
- W4386896750 date "2023-09-20" @default.
- W4386896750 modified "2023-10-02" @default.
- W4386896750 title "FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphs" @default.
- W4386896750 cites W1669094309 @default.
- W4386896750 cites W2131681506 @default.
- W4386896750 cites W4290945652 @default.
- W4386896750 doi "https://doi.org/10.1145/3624017" @default.
- W4386896750 hasPublicationYear "2023" @default.
- W4386896750 type Work @default.
- W4386896750 citedByCount "1" @default.
- W4386896750 countsByYear W43868967502023 @default.
- W4386896750 crossrefType "journal-article" @default.
- W4386896750 hasAuthorship W4386896750A5000582109 @default.
- W4386896750 hasAuthorship W4386896750A5028890544 @default.
- W4386896750 hasAuthorship W4386896750A5041581408 @default.
- W4386896750 hasAuthorship W4386896750A5069084441 @default.
- W4386896750 hasAuthorship W4386896750A5075696732 @default.
- W4386896750 hasAuthorship W4386896750A5084807160 @default.
- W4386896750 hasBestOaLocation W43868967501 @default.
- W4386896750 hasConcept C119857082 @default.
- W4386896750 hasConcept C124101348 @default.
- W4386896750 hasConcept C132525143 @default.
- W4386896750 hasConcept C136764020 @default.
- W4386896750 hasConcept C154945302 @default.
- W4386896750 hasConcept C183003079 @default.
- W4386896750 hasConcept C41008148 @default.
- W4386896750 hasConcept C80444323 @default.
- W4386896750 hasConceptScore W4386896750C119857082 @default.
- W4386896750 hasConceptScore W4386896750C124101348 @default.
- W4386896750 hasConceptScore W4386896750C132525143 @default.
- W4386896750 hasConceptScore W4386896750C136764020 @default.
- W4386896750 hasConceptScore W4386896750C154945302 @default.
- W4386896750 hasConceptScore W4386896750C183003079 @default.
- W4386896750 hasConceptScore W4386896750C41008148 @default.
- W4386896750 hasConceptScore W4386896750C80444323 @default.
- W4386896750 hasLocation W43868967501 @default.
- W4386896750 hasOpenAccess W4386896750 @default.
- W4386896750 hasPrimaryLocation W43868967501 @default.
- W4386896750 hasRelatedWork W2108595774 @default.
- W4386896750 hasRelatedWork W2961085424 @default.
- W4386896750 hasRelatedWork W3046775127 @default.
- W4386896750 hasRelatedWork W3170094116 @default.
- W4386896750 hasRelatedWork W4285260836 @default.
- W4386896750 hasRelatedWork W4286629047 @default.
- W4386896750 hasRelatedWork W4306321456 @default.
- W4386896750 hasRelatedWork W4306674287 @default.
- W4386896750 hasRelatedWork W87991986 @default.
- W4386896750 hasRelatedWork W4224009465 @default.
- W4386896750 isParatext "false" @default.
- W4386896750 isRetracted "false" @default.
- W4386896750 workType "article" @default.