Pith. sign in

REVIEW 1 cited by

Decentralized Personalized Federated Learning based on a Conditional Sparse-to-Sparser Scheme

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 2404.15943 v3 pith:55TI5CJK submitted 2024-04-24 cs.LG cs.AI

classification cs.LGcs.AI
keywords da-dpfltraininglearningdecentralizedcommunicationcostsduringenergy
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Decentralized Federated Learning (DFL) has become popular due to its robustness and avoidance of centralized coordination. In this paradigm, clients actively engage in training by exchanging models with their networked neighbors. However, DFL introduces increased costs in terms of training and communication. Existing methods focus on minimizing communication often overlooking training efficiency and data heterogeneity. To address this gap, we propose a novel \textit{sparse-to-sparser} training scheme: DA-DPFL. DA-DPFL initializes with a subset of model parameters, which progressively reduces during training via \textit{dynamic aggregation} and leads to substantial energy savings while retaining adequate information during critical learning periods. Our experiments showcase that DA-DPFL substantially outperforms DFL baselines in test accuracy, while achieving up to $5$ times reduction in energy costs. We provide a theoretical analysis of DA-DPFL's convergence by solidifying its applicability in decentralized and personalized learning. The code is available at:https://github.com/EricLoong/da-dpfl

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. S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning

    cs.LG 2025-01 conditional novelty 4.0 of 10

    S-VOTE selects clients by cosine similarity of model weights and lets low-vote clients sometimes skip training, reducing communication and energy while improving non-IID accuracy in some settings.

Pith tools