Pith. sign in

REVIEW 7 cited by

Federated Learning of a Mixture of Global and 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 2002.05516 v3 pith:WGWU4TOQ submitted 2020-02-10 cs.LG cs.DCmath.OCstat.ML

classification cs.LGcs.DCmath.OCstat.ML
keywords localcommunicationfederatedformulationdatagloballearningmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a new optimization formulation for training federated learning models. The standard formulation has the form of an empirical risk minimization problem constructed to find a single global model trained from the private data stored across all participating devices. In contrast, our formulation seeks an explicit trade-off between this traditional global model and the local models, which can be learned by each device from its own private data without any communication. Further, we develop several efficient variants of SGD (with and without partial participation and with and without variance reduction) for solving the new formulation and prove communication complexity guarantees. Notably, our methods are similar but not identical to federated averaging / local SGD, thus shedding some light on the role of local steps in federated learning. In particular, we are the first to i) show that local steps can improve communication for problems with heterogeneous data, and ii) point out that personalization yields reduced communication complexity.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Robust Decentralized Optimization under Node Failures via Adaptive Regularization

    math.OC 2026-07 accept novelty 7.0 of 10

    Legacy-GT lets a departing node hand a gradient-anchored quadratic surrogate and tracker correction to one neighbor, yielding geometrically decaying residual bias instead of permanent drop-and-forget bias.

  2. Collaborative and Efficient Fine-tuning: Leveraging Task Similarity

    cs.LG 2026-02 conditional novelty 6.0 of 10

    CoLoRA shares a low-rank adapter pair across users plus a small personal matrix, improving fine-tuning for similar tasks and providing a recovery guarantee.

  3. DICE: Data Influence Cascade in Decentralized Learning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    DICE defines and approximates multi-hop data influence in decentralized learning, showing that influence is shaped by data, topology, and loss curvature.

  4. SPIRE: Conditional Personalization for Federated Diffusion Generative Models

    cs.LG 2025-06 reject novelty 6.0 of 10

    SPIRE adds per-client embeddings to a shared diffusion backbone, enabling parameter-efficient personalization in federated learning, with new-client KID improvements on MNIST, CIFAR-10, and CelebA.

  5. Decoding FL Defenses: Systemization, Pitfalls, and Remedies

    cs.CR 2025-02 conditional novelty 6.0 of 10

    Many FL defenses are evaluated on overly easy datasets and attacks, and this paper demonstrates with case studies that those easy settings can make weak defenses look strong.

  6. Optimization Methods and Software for Federated Learning

    cs.LG 2025-09 conditional novelty 4.0 of 10

    A thesis that packages the author's published federated learning work, whose main new theoretical result is an improved complexity bound for error-feedback compression.

  7. Strategies for Improving Communication Efficiency in Distributed and Federated Learning: Compression, Local Training, and Personalization

    cs.LG 2025-09 conditional novelty 3.0 of 10

    A PhD dissertation showing unified compression theory, personalized accelerated local training, and pruning methods that reduce communication costs in federated learning and maintain accuracy in LLM pruning.

Pith tools