FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386075205> ?p ?o ?g. }

• W4386075205 abstract "State-of-the-art federated learning algorithms are faced with many critical challenges that limit their applications in many domains. The vanilla federated learning architecture contains a central server that coordinates the training process. However, the central server is prone to congestion and a single point of failure as the number of clients grows exponentially. More so, the state-of-the-art federated learning algorithms are designed for fixed data distributions. Yet in many real-world scenarios, such as in real-time traffic monitoring systems, the data distribution of each client is time-varying. Hence, such algorithms do not perform well in these scenarios. Another challenge is that a single trained global model in federated learning may not perform optimally on the test dataset of any client since each client may have a specific task it aims to achieve despite task relatedness among clients. A more serious challenge caused by high data heterogeneity among the clients’ dataset is the unfairness of the trained model towards a minority group. Minority groups are classified by race, gender, social status, etc. This unfairness occurs when the trained global model discriminates against minority groups even when a local model is bias-free. Therefore, this paper addresses these challenges by proposing the Differentially private Personalized Online Federated Learning (DIPOFEL) and Differentially private Personalized Online Federated Learning with FAIRness (DIPOFLAIR) Algorithms for a peer-to-peer federated learning setting reinforced with local differential privacy. DIPOFEL Algorithm employs the online learning technique to handle time-varying data distribution, the meta-learning technique to personalize the trained model to each client’s specific task, and local differential privacy to prevent reconstruction attacks on the global model. DIPOFLAIR Algorithm is based on a constrained optimization problem that is solved using a Lagrangian approach with DIPOFEL Algorithm as a subroutine. The simulation result shows that the regret bounds of the proposed algorithms are better than the state-of-the-art algorithms." @default.
• W4386075205 created "2023-08-23" @default.
• W4386075205 creator A5035313713 @default.
• W4386075205 date "2023-06-25" @default.
• W4386075205 modified "2023-09-27" @default.
• W4386075205 title "Differentially Private Online Federated Learning With Personalization and Fairness" @default.
• W4386075205 cites W1964042213 @default.
• W4386075205 cites W2053801139 @default.
• W4386075205 cites W2109426455 @default.
• W4386075205 cites W2980713544 @default.
• W4386075205 cites W2981869278 @default.
• W4386075205 cites W3001299093 @default.
• W4386075205 cites W3016632787 @default.
• W4386075205 cites W3027749727 @default.
• W4386075205 cites W3109847748 @default.
• W4386075205 cites W3129329365 @default.
• W4386075205 cites W3136022984 @default.
• W4386075205 cites W3175574903 @default.
• W4386075205 cites W3176639943 @default.
• W4386075205 cites W3197458050 @default.
• W4386075205 cites W4205841652 @default.
• W4386075205 cites W4207013366 @default.
• W4386075205 cites W4221100464 @default.
• W4386075205 cites W4225724416 @default.
• W4386075205 cites W4226461837 @default.
• W4386075205 doi "https://doi.org/10.1109/isit54713.2023.10206945" @default.
• W4386075205 hasPublicationYear "2023" @default.
• W4386075205 type Work @default.
• W4386075205 citedByCount "0" @default.
• W4386075205 crossrefType "proceedings-article" @default.
• W4386075205 hasAuthorship W4386075205A5035313713 @default.
• W4386075205 hasConcept C111919701 @default.
• W4386075205 hasConcept C119857082 @default.
• W4386075205 hasConcept C120314980 @default.
• W4386075205 hasConcept C124101348 @default.
• W4386075205 hasConcept C136764020 @default.
• W4386075205 hasConcept C154945302 @default.
• W4386075205 hasConcept C162324750 @default.
• W4386075205 hasConcept C165136773 @default.
• W4386075205 hasConcept C183003079 @default.
• W4386075205 hasConcept C187736073 @default.
• W4386075205 hasConcept C23130292 @default.
• W4386075205 hasConcept C2780451532 @default.
• W4386075205 hasConcept C2992525071 @default.
• W4386075205 hasConcept C41008148 @default.
• W4386075205 hasConcept C75684735 @default.
• W4386075205 hasConcept C98045186 @default.
• W4386075205 hasConceptScore W4386075205C111919701 @default.
• W4386075205 hasConceptScore W4386075205C119857082 @default.
• W4386075205 hasConceptScore W4386075205C120314980 @default.
• W4386075205 hasConceptScore W4386075205C124101348 @default.
• W4386075205 hasConceptScore W4386075205C136764020 @default.
• W4386075205 hasConceptScore W4386075205C154945302 @default.
• W4386075205 hasConceptScore W4386075205C162324750 @default.
• W4386075205 hasConceptScore W4386075205C165136773 @default.
• W4386075205 hasConceptScore W4386075205C183003079 @default.
• W4386075205 hasConceptScore W4386075205C187736073 @default.
• W4386075205 hasConceptScore W4386075205C23130292 @default.
• W4386075205 hasConceptScore W4386075205C2780451532 @default.
• W4386075205 hasConceptScore W4386075205C2992525071 @default.
• W4386075205 hasConceptScore W4386075205C41008148 @default.
• W4386075205 hasConceptScore W4386075205C75684735 @default.
• W4386075205 hasConceptScore W4386075205C98045186 @default.
• W4386075205 hasLocation W43860752051 @default.
• W4386075205 hasOpenAccess W4386075205 @default.
• W4386075205 hasPrimaryLocation W43860752051 @default.
• W4386075205 hasRelatedWork W2978648093 @default.
• W4386075205 hasRelatedWork W3014300295 @default.
• W4386075205 hasRelatedWork W3018102029 @default.
• W4386075205 hasRelatedWork W3166318610 @default.
• W4386075205 hasRelatedWork W3213663322 @default.
• W4386075205 hasRelatedWork W4213404037 @default.
• W4386075205 hasRelatedWork W4226111152 @default.
• W4386075205 hasRelatedWork W4286340214 @default.
• W4386075205 hasRelatedWork W4298164042 @default.
• W4386075205 hasRelatedWork W4226283875 @default.
• W4386075205 isParatext "false" @default.
• W4386075205 isRetracted "false" @default.
• W4386075205 workType "article" @default.