Pith. sign in

REVIEW 1 cited by

FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization

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 2305.02894 v1 pith:XGWW2NV6 submitted 2023-05-04 cs.LG math.APmath.OCstat.ML

FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization

classification cs.LG math.APmath.OCstat.ML
keywords learningfederatedgroupusersclusteredoptimizationconsensus-baseddata
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Federated learning is an important framework in modern machine learning that seeks to integrate the training of learning models from multiple users, each user having their own local data set, in a way that is sensitive to data privacy and to communication loss constraints. In clustered federated learning, one assumes an additional unknown group structure among users, and the goal is to train models that are useful for each group, rather than simply training a single global model for all users. In this paper, we propose a novel solution to the problem of clustered federated learning that is inspired by ideas in consensus-based optimization (CBO). Our new CBO-type method is based on a system of interacting particles that is oblivious to group memberships. Our model is motivated by rigorous mathematical reasoning, including a mean field analysis describing the large number of particles limit of our particle system, as well as convergence guarantees for the simultaneous global optimization of general non-convex objective functions (corresponding to the loss functions of each cluster of users) in the mean-field regime. Experimental results demonstrate the efficacy of our FedCBO algorithm compared to other state-of-the-art methods and help validate our methodological and theoretical work.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

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

  1. Consensus-Based Optimization with Truncated Noise

    math.OC 2023-10 unverdicted novelty 6.0

    Truncating noise in CBO bounds higher moments of the particle law and enables a rigorous proof of convergence in expectation to the global minimizer via Wasserstein-2 distance analysis under minimal assumptions.