decentralized-learning

Tag

Cards List
#decentralized-learning

Serverless gossip training of LSTM failure detectors: A matched-protocol comparison with federated, local and centralized learning on NASA C-MAPSS

arXiv cs.LG ↗ · 13h ago Cached

A matched-protocol comparison of synchronous ring gossip, FedAvg, local and centralized training for LSTM failure detectors on the NASA C-MAPSS turbofan benchmark, showing gossip as a practical serverless alternative to federated averaging that matches FedAvg performance without a coordinator.

0 favorites 0 likes
#decentralized-learning

CALM: Class-wise Agreement and Label-gated Disagreement Modulation for Decentralized Federated Learning

arXiv cs.LG ↗ · 2026-09-10 Cached

CALM proposes a method for decentralized federated learning that uses class-wise agreement and label-gated disagreement modulation to handle non-IID data, improving teacher weighting and distillation trust without additional communication overhead.

0 favorites 0 likes
#decentralized-learning

Convergence Theory of Knowledge Distillation in Asynchronous P2P Gossip Learning Network

arXiv cs.LG ↗ · 2026-09-03 Cached

This paper provides convergence theory for knowledge distillation in asynchronous peer-to-peer gossip learning networks, demonstrating that it contracts function disagreement and analyzing theoretical convergence rates.

0 favorites 0 likes
#decentralized-learning

CRAD: Class-wise Reliability-Aware Distillation for Decentralized Heterogeneous Federated Learning

arXiv cs.LG ↗ · 2026-09-02 Cached

The paper proposes CRAD, a class-wise reliability-aware distillation method for decentralized federated learning to handle heterogeneous architectures and non-IID data, achieving improved accuracy on image classification benchmarks.

0 favorites 0 likes
#decentralized-learning

RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks

arXiv cs.LG ↗ · 2026-09-02 Cached

This paper introduces RW-LoRA, a decentralized LoRA fine-tuning method using random walks to reduce communication and computation costs while achieving competitive performance on NLP tasks.

0 favorites 0 likes
#decentralized-learning

A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraints

arXiv cs.LG ↗ · 2026-08-28 Cached

This paper proposes a unified framework for decentralized learning under communication constraints, introducing the DMFL-SQ algorithm that combines graph-based personalization, agnostic fairness, and compressed communication to achieve reduced communication while maintaining predictive performance and improving fairness across clients.

0 favorites 0 likes
#decentralized-learning

Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry

arXiv cs.LG ↗ · 2026-08-14 Cached

This paper studies decentralized multi-player Q-learning in episodic Markov decision processes under three forms of information asymmetry, proposing algorithms that achieve regret bounds matching the single-agent Q-learning rate up to logarithmic factors.

0 favorites 0 likes
#decentralized-learning

MEMOA: Massive Mixtures of Online Agents via Mean-Field Decentralized Nash Equilibria

arXiv cs.LG ↗ · 2026-05-08 Cached

The paper introduces MEMOA, a decentralized strategy for massive online agents that achieves optimality via mean-field Nash equilibria, outperforming greedy baselines while scaling better than centralized approaches.

0 favorites 0 likes
← Back to home

Submit Feedback