Personalized Collaborative Learning with Affinity-Based Variance Reduction
Not on the map. Why?
Abstract (arXiv)
Multi-agent learning faces a fundamental tension: leveraging distributed collaboration without sacrificing the personalization needed for diverse agents. This tension intensifies when aiming for full personalization while adapting to unknown heterogeneity levels -- gaining collaborative speedup when agents are similar, without performance degradation when they are different. Embracing the challenge, we propose personalized collaborative learning (PCL), a novel framework for heterogeneous agents to collaboratively learn personalized solutions with seamless adaptivity. Through carefully designed bias correction and importance correction mechanisms, our method AffPCL robustly handles both environment and objective heterogeneity. We prove that AffPCL reduces sample complexity over independent learning by a factor of maxn-1, δ, where n is the number of agents and δ∈[0,1] measures their heterogeneity. This affinity-based acceleration automatically interpolates between the linear speedup of federated learning in homogeneous settings and the baseline of independent learning, without requiring prior knowledge of the system. Our analysis further reveals that an agent may obtain linear speedup even by collaborating with arbitrarily dissimilar agents, unveiling new insights into personalization and collaboration in the high heterogeneity regime.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 39 of its 63 references that are in the map. First posted on arXiv 17 Oct 2025.
Builds on
39 of 63 references.
References · 39
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
- 2020Personalized Federated Learning with Moreau Envelopescited by 612
- 2020An Efficient Framework for Clustered Federated Learningcited by 505
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
- 2014SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectivescited by 401
- 2020Adaptive Personalized Federated Learningcited by 353
- 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
- 2016Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learningcited by 285
- 2018A Finite Time Analysis of Temporal Difference Learning With Linear Function Approximationcited by 225
27 more
- 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
- 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
- 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
- 2020Mime: Mimicking Centralized Stochastic Algorithms in Federated Learningcited by 152
- 2020Is Local SGD Better than Minibatch SGD?cited by 151
- 2024Personalized Language Modeling from Personalized Human Feedbackcited by 124
- 2022Federated Learning with Partial Model Personalizationcited by 114
- 2020TiFL: A Tier-based Federated Learning Systemcited by 95
- 2022Optimally tackling covariate shift in RKHS-based nonparametric regressioncited by 53
- 2024Personalized Large Language Modelscited by 44
- 2021Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspectivecited by 38
- 2022FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reductioncited by 35
- 2025LoRe: Personalizing LLMs via Low-Rank Reward Modelingcited by 34
- 2024Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learningcited by 29
- 2025Activation-Informed Merging of Large Language Modelscited by 29
- 2023Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneitycited by 25
- 2022Control-oriented meta-learningcited by 17
- 2021Linear Speedup in Personalized Collaborative Learningcited by 8
- 2021Optimal Model Averaging: Towards Personalized Collaborative Learningcited by 7
- 2024SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learningcited by 6
- 2024Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximationcited by 5
- 2024Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibriumcited by 5
- 2022Online Learning for Traffic Routing under Unknown Preferencescited by 4
- 2024On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representationscited by 4
- 2017Distributed Solution of Large-Scale Linear Systems via Accelerated Projection-Based Consensuscited by 3
- 2022Sample Optimality and All-for-all Strategies in Personalized Federated and Collaborative Learningcited by 3
- 2024Meta-Learning for Adaptive Control with Automated Mirror Descentcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.