Pith. sign in

REVIEW 5 cited by

Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2010.01243 v1 pith:EYVOJMLB submitted 2020-10-03 cs.LG cs.DCstat.ML

Yae Jee Cho , Jianyu Wang , Gauri Joshi This is my paper · ORCID
classification cs.LGcs.DCstat.ML
keywords clientselectionconvergencefederateddatalearningpower-of-choicestrategies
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Federated learning is a distributed optimization paradigm that enables a large number of resource-limited client nodes to cooperatively train a model without data sharing. Several works have analyzed the convergence of federated learning by accounting of data heterogeneity, communication and computation limitations, and partial client participation. However, they assume unbiased client participation, where clients are selected at random or in proportion of their data sizes. In this paper, we present the first convergence analysis of federated optimization for biased client selection strategies, and quantify how the selection bias affects convergence speed. We reveal that biasing client selection towards clients with higher local loss achieves faster error convergence. Using this insight, we propose Power-of-Choice, a communication- and computation-efficient client selection framework that can flexibly span the trade-off between convergence speed and solution bias. Our experiments demonstrate that Power-of-Choice strategies converge up to 3 $\times$ faster and give $10$% higher test accuracy than the baseline random selection.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation

    cs.LG 2025-09 conditional novelty 6.0 of 10

    D-Byz-SGDM aggregates cached momentum from non-sampled clients together with fresh momentum from sampled clients, preserving Byzantine robustness under partial participation and achieving an optimal O(cδζ²/p) stationa...

  2. Green Federated Learning via Carbon-Aware Client and Time Slot Scheduling

    cs.LG 2025-09 conditional novelty 5.0 of 10

    A carbon-aware federated learning scheduler that adds slack time, fair client selection, and fine-tuning beats a full-participation baseline on MNIST under tight carbon budgets.

  3. PFedDST: Personalized Federated Learning with Decentralized Selection Training

    cs.LG 2025-02 reject novelty 4.0 of 10

    A decentralized personalized federated learning method that scores peers by loss, header similarity, and recency reports faster convergence, but its own CIFAR-100 result contradicts the accuracy claim.

  4. Incentive-Compatible Federated Learning with Stackelberg Game Modeling

    cs.LG 2025-01 reject novelty 4.0 of 10

    FLamma claims to balance fairness and accuracy in federated learning via a Stackelberg game with an adaptive decay factor, but the theory has derivation errors and the experiments use fixed local epochs.

  5. Stackelberg Game Based Performance Optimization in Digital Twin Assisted Federated Learning over NOMA Networks

    cs.LG 2025-01 reject novelty 4.0 of 10

    For digital twin assisted federated learning over NOMA, the paper derives a Stackelberg equilibrium for mapping ratio, local frequency, and transmit power, with reputation-based selection to resist poisoning attacks.

Pith tools