在通信受限下，实现公平且个性化的去中心化学习。
A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraints
- 通过图结构个性化与事件触发通信降低通信开销。
- 理论证明收敛速率达O(T^{-1/2})，且在真实数据集上提升公平性。
- 适合关注隐私、效率与公平的分布式学习研究者。
去中心化学习系统旨在无需中心协调器的情况下，跨多个客户端协同训练模型。尽管去中心化提升了可扩展性、隐私性和鲁棒性，但也加剧了三个根本挑战：客户端间的统计异质性、客户端层面的公平性以及严格的通信约束。这引出一个核心问题：在通信受限条件下，去中心化学习能有多公平？为此，本文提出一个统一框架，整合基于图的个性化、无假设公平性及压缩事件触发通信。具体地，提出新算法DMFL-SQ，一种去中心化多任务学习算法，将通信图上的个性化模型训练与无假设混合公平目标相结合，同时通过稀疏化、量化和事件触发同步减少通信。我们为一般非凸目标建立了收敛性保证，证明在稀疏、量化、事件触发通信下，DMFL-SQ仍能达到期望平方Moreau包络平稳性的$/mathcal{O}(T^{-1/2})$收敛率。进一步推导了公平感知混合目标的PAC-Bayes泛化界。在CIFAR-10和真实异构MUSMET EEG数据集上的实验表明，DMFL-SQ显著降低通信量，同时保持预测性能并提升客户端间公平性。理论与实证结果共同表明，在保持主导收敛率的前提下，去中心化学习中个性化、公平性与通信效率可协同实现。
原文摘要 · Abstract (English)
Decentralized learning systems aim to collaboratively train models across multiple clients without relying on a central coordinator. While decentralization improves scalability, privacy, and robustness, it also exacerbates three fundamental challenges: statistical heterogeneity across clients, fairness in client-level performance, and stringent communication constraints. This raises a natural question: \emph{how fair can decentralized learning be under limited communication?} We address this question by presenting a unified framework for decentralized learning under communication constraints, bringing together graph-based personalization, agnostic fairness, and compressed event-triggered communication. Specifically, we propose a new algorithm DMFL-SQ, a decentralized multi-task learning algorithm that couples personalized model training over a communication graph with an agnostic mixture fairness objective, while reducing communication through sparsification, quantization, and event-triggered synchronization. We establish convergence guarantees for general non-convex objectives and show that DMFL-SQ achieves an $\mathcal{O}(T^{-1/2})$ rate in expected squared Moreau-envelope stationarity despite sparse, quantized, and event-triggered communication. We further derive PAC-Bayes generalization guarantees for the fairness-aware mixture objective. Experiments on CIFAR-10 and the real heterogeneous MUSMET EEG dataset demonstrate that DMFL-SQ substantially reduces communication while maintaining predictive performance and improving fairness across clients. Together, our theoretical and empirical results show that personalization, fairness, and communication efficiency can be jointly achieved in decentralized learning while preserving the dominant convergence rate.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。