Pith. sign in

REVIEW 1 cited by

Achieving Personalized Federated Learning with Sparse Local Models

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

arxiv 2201.11380 v1 pith:HKPVQAS7 submitted 2022-01-27 cs.LG cs.AIcs.DC

classification cs.LGcs.AIcs.DC
keywords fedspalocalmodelmodelspersonalizedsparsecomputationfederated
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Federated learning (FL) is vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user. To counter this issue, personalized FL (PFL) was proposed to produce dedicated local models for each individual user. However, PFL is far from its maturity, because existing PFL solutions either demonstrate unsatisfactory generalization towards different model architectures or cost enormous extra computation and memory. In this work, we propose federated learning with personalized sparse mask (FedSpa), a novel PFL scheme that employs personalized sparse masks to customize sparse local models on the edge. Instead of training an intact (or dense) PFL model, FedSpa only maintains a fixed number of active parameters throughout training (aka sparse-to-sparse training), which enables users' models to achieve personalization with cheap communication, computation, and memory cost. We theoretically show that the iterates obtained by FedSpa converge to the local minimizer of the formulated SPFL problem at rate of $\mathcal{O}(\frac{1}{\sqrt{T}})$. Comprehensive experiments demonstrate that FedSpa significantly saves communication and computation costs, while simultaneously achieves higher model accuracy and faster convergence speed against several state-of-the-art PFL methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity

    cs.LG 2025-06 conditional novelty 6.0 of 10

    LIPS, a method that periodically prunes low-sensitivity middle-layer weights after aggregation, mitigates layer-wise inertia and improves low-data federated learning accuracy.

Pith tools