Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386075249> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W4386075249 abstract "In this paper, we study training a classifier satisfying local fairness constraints via federated learning. We compare two schemes: local fair training (LFT) combined with the ensemble method (LFT+Ensemble), and LFT combined with federated averaging (LFT+FedAvg). Our theoretical analysis shows that (i) LFT+FedAvg outperforms LFT+Ensemble in terms of fairness at the cost of frequent communication, and (ii) LFT+FedAvg may not reach the optimal fairness achievable through centralized training. The findings explain the success of recently proposed federated learning algorithms that virtually compute global fairness constraints with additional communication rounds. Moreover, we also present numerical experiments that support our findings in more general settings." @default.
- W4386075249 created "2023-08-23" @default.
- W4386075249 creator A5009606065 @default.
- W4386075249 creator A5065836136 @default.
- W4386075249 creator A5073193050 @default.
- W4386075249 date "2023-06-25" @default.
- W4386075249 modified "2023-09-27" @default.
- W4386075249 title "Federated Learning with Local Fairness Constraints" @default.
- W4386075249 cites W2100960835 @default.
- W4386075249 cites W2963116854 @default.
- W4386075249 cites W3198906045 @default.
- W4386075249 cites W4289258088 @default.
- W4386075249 doi "https://doi.org/10.1109/isit54713.2023.10206590" @default.
- W4386075249 hasPublicationYear "2023" @default.
- W4386075249 type Work @default.
- W4386075249 citedByCount "0" @default.
- W4386075249 crossrefType "proceedings-article" @default.
- W4386075249 hasAuthorship W4386075249A5009606065 @default.
- W4386075249 hasAuthorship W4386075249A5065836136 @default.
- W4386075249 hasAuthorship W4386075249A5073193050 @default.
- W4386075249 hasConcept C11867375 @default.
- W4386075249 hasConcept C119857082 @default.
- W4386075249 hasConcept C126255220 @default.
- W4386075249 hasConcept C154945302 @default.
- W4386075249 hasConcept C157764524 @default.
- W4386075249 hasConcept C2992525071 @default.
- W4386075249 hasConcept C33923547 @default.
- W4386075249 hasConcept C41008148 @default.
- W4386075249 hasConcept C45942800 @default.
- W4386075249 hasConcept C555944384 @default.
- W4386075249 hasConcept C76155785 @default.
- W4386075249 hasConcept C95623464 @default.
- W4386075249 hasConceptScore W4386075249C11867375 @default.
- W4386075249 hasConceptScore W4386075249C119857082 @default.
- W4386075249 hasConceptScore W4386075249C126255220 @default.
- W4386075249 hasConceptScore W4386075249C154945302 @default.
- W4386075249 hasConceptScore W4386075249C157764524 @default.
- W4386075249 hasConceptScore W4386075249C2992525071 @default.
- W4386075249 hasConceptScore W4386075249C33923547 @default.
- W4386075249 hasConceptScore W4386075249C41008148 @default.
- W4386075249 hasConceptScore W4386075249C45942800 @default.
- W4386075249 hasConceptScore W4386075249C555944384 @default.
- W4386075249 hasConceptScore W4386075249C76155785 @default.
- W4386075249 hasConceptScore W4386075249C95623464 @default.
- W4386075249 hasLocation W43860752491 @default.
- W4386075249 hasOpenAccess W4386075249 @default.
- W4386075249 hasPrimaryLocation W43860752491 @default.
- W4386075249 hasRelatedWork W2810053714 @default.
- W4386075249 hasRelatedWork W3200179079 @default.
- W4386075249 hasRelatedWork W3202701980 @default.
- W4386075249 hasRelatedWork W4205754593 @default.
- W4386075249 hasRelatedWork W4281560664 @default.
- W4386075249 hasRelatedWork W4281757034 @default.
- W4386075249 hasRelatedWork W4285046548 @default.
- W4386075249 hasRelatedWork W4285741730 @default.
- W4386075249 hasRelatedWork W4311847748 @default.
- W4386075249 hasRelatedWork W4313488044 @default.
- W4386075249 isParatext "false" @default.
- W4386075249 isRetracted "false" @default.
- W4386075249 workType "article" @default.