Matches in SemOpenAlex for { <https://semopenalex.org/work/W4229041027> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4229041027 abstract "Since federated learning (FL) has been introduced as a decentralized learning technique with privacy preservation, statistical heterogeneity of distributed data stays the main obstacle to achieve robust performance and stable convergence in FL applications. Model personalization methods have been studied to overcome this problem. However, existing approaches are mainly under the prerequisite of fully labeled data, which is unrealistic in practice due to the requirement of expertise. The primary issue caused by partial-labeled condition is that, clients with deficient labeled data can suffer from unfair performance gain because they lack adequate insights of local distribution to customize the global model. To tackle this problem, 1) we propose a novel personalized semi-supervised learning paradigm which allows partial-labeled or unlabeled clients to seek labeling assistance from data-related clients (helper agents), thus to enhance their perception of local data; 2) based on this paradigm, we design an uncertainty-based data-relation metric to ensure that selected helpers can provide trustworthy pseudo labels instead of misleading the local training; 3) to mitigate the network overload introduced by helper searching, we further develop a helper selection protocol to achieve efficient communication with negligible performance sacrifice. Experiments show that our proposed method can obtain superior performance and more stable convergence than other related works with partial labeled data, especially in highly heterogeneous setting." @default.
- W4229041027 created "2022-05-08" @default.
- W4229041027 creator A5040264802 @default.
- W4229041027 creator A5041294009 @default.
- W4229041027 creator A5088291390 @default.
- W4229041027 date "2022-05-05" @default.
- W4229041027 modified "2023-10-14" @default.
- W4229041027 title "Uncertainty Minimization for Personalized Federated Semi-Supervised Learning" @default.
- W4229041027 doi "https://doi.org/10.48550/arxiv.2205.02438" @default.
- W4229041027 hasPublicationYear "2022" @default.
- W4229041027 type Work @default.
- W4229041027 citedByCount "0" @default.
- W4229041027 crossrefType "posted-content" @default.
- W4229041027 hasAuthorship W4229041027A5040264802 @default.
- W4229041027 hasAuthorship W4229041027A5041294009 @default.
- W4229041027 hasAuthorship W4229041027A5088291390 @default.
- W4229041027 hasBestOaLocation W42290410271 @default.
- W4229041027 hasConcept C105795698 @default.
- W4229041027 hasConcept C119857082 @default.
- W4229041027 hasConcept C124101348 @default.
- W4229041027 hasConcept C136764020 @default.
- W4229041027 hasConcept C142724271 @default.
- W4229041027 hasConcept C154945302 @default.
- W4229041027 hasConcept C162324750 @default.
- W4229041027 hasConcept C176217482 @default.
- W4229041027 hasConcept C17744445 @default.
- W4229041027 hasConcept C183003079 @default.
- W4229041027 hasConcept C199539241 @default.
- W4229041027 hasConcept C204787440 @default.
- W4229041027 hasConcept C21547014 @default.
- W4229041027 hasConcept C25343380 @default.
- W4229041027 hasConcept C2776650193 @default.
- W4229041027 hasConcept C2777303404 @default.
- W4229041027 hasConcept C2780385302 @default.
- W4229041027 hasConcept C2780598303 @default.
- W4229041027 hasConcept C33923547 @default.
- W4229041027 hasConcept C41008148 @default.
- W4229041027 hasConcept C50522688 @default.
- W4229041027 hasConcept C71924100 @default.
- W4229041027 hasConceptScore W4229041027C105795698 @default.
- W4229041027 hasConceptScore W4229041027C119857082 @default.
- W4229041027 hasConceptScore W4229041027C124101348 @default.
- W4229041027 hasConceptScore W4229041027C136764020 @default.
- W4229041027 hasConceptScore W4229041027C142724271 @default.
- W4229041027 hasConceptScore W4229041027C154945302 @default.
- W4229041027 hasConceptScore W4229041027C162324750 @default.
- W4229041027 hasConceptScore W4229041027C176217482 @default.
- W4229041027 hasConceptScore W4229041027C17744445 @default.
- W4229041027 hasConceptScore W4229041027C183003079 @default.
- W4229041027 hasConceptScore W4229041027C199539241 @default.
- W4229041027 hasConceptScore W4229041027C204787440 @default.
- W4229041027 hasConceptScore W4229041027C21547014 @default.
- W4229041027 hasConceptScore W4229041027C25343380 @default.
- W4229041027 hasConceptScore W4229041027C2776650193 @default.
- W4229041027 hasConceptScore W4229041027C2777303404 @default.
- W4229041027 hasConceptScore W4229041027C2780385302 @default.
- W4229041027 hasConceptScore W4229041027C2780598303 @default.
- W4229041027 hasConceptScore W4229041027C33923547 @default.
- W4229041027 hasConceptScore W4229041027C41008148 @default.
- W4229041027 hasConceptScore W4229041027C50522688 @default.
- W4229041027 hasConceptScore W4229041027C71924100 @default.
- W4229041027 hasLocation W42290410271 @default.
- W4229041027 hasOpenAccess W4229041027 @default.
- W4229041027 hasPrimaryLocation W42290410271 @default.
- W4229041027 hasRelatedWork W10786582 @default.
- W4229041027 hasRelatedWork W11297145 @default.
- W4229041027 hasRelatedWork W11356396 @default.
- W4229041027 hasRelatedWork W12461812 @default.
- W4229041027 hasRelatedWork W2383694 @default.
- W4229041027 hasRelatedWork W3422034 @default.
- W4229041027 hasRelatedWork W482614 @default.
- W4229041027 hasRelatedWork W5990143 @default.
- W4229041027 hasRelatedWork W7092785 @default.
- W4229041027 hasRelatedWork W6316171 @default.
- W4229041027 isParatext "false" @default.
- W4229041027 isRetracted "false" @default.
- W4229041027 workType "article" @default.