REVIEW 3 cited by
Federated Evaluation of On-device Personalization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Federated Evaluation of On-device Personalization
read the original abstract
Federated learning is a distributed, on-device computation framework that enables training global models without exporting sensitive user data to servers. In this work, we describe methods to extend the federation framework to evaluate strategies for personalization of global models. We present tools to analyze the effects of personalization and evaluate conditions under which personalization yields desirable models. We report on our experiments personalizing a language model for a virtual keyboard for smartphones with a population of tens of millions of users. We show that a significant fraction of users benefit from personalization.
Forward citations
Cited by 3 Pith papers
-
FedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture
A semiparametric mixture federated model with density-ratio routing and a federated EM algorithm improves routing and prediction under joint inter- and intra-client heterogeneity.
-
Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems
Collate jointly trains heterogeneous models under per-device latency constraints via dynamic zeroizing-recovering and proto-corrected aggregation, gaining ~2–3% accuracy over prior heterogeneous FL.
-
FedRio: Personalized Federated Social Bot Detection via Cooperative Reinforced Contrastive Adversarial Distillation
FedRio is a new federated framework that outperforms standard federated baselines in social bot detection accuracy and efficiency while staying competitive with centralized models under stronger privacy constraints.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.