Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID Data
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) enables distributed training of machine learning models while preserving data privacy. However, FL struggles with heterogeneous, non-IID client data distributions, resulting in sub-optimal and biased global models. In this paper, we propose pFedMARL, a novel approach leveraging Multi-Agent Reinforcement Learning (MARL) with Twin Delayed Deep Deterministic Policy Gradient (TD3) to dynamically adapt aggregation strategies in FL settings. Our method employs a server-side agent adjusting client contributions to optimize global model robustness and client-side agents balancing global and local updates to personalize models effectively without pre-training. We demonstrate superior performance of pFedMARL for training a semi-supervised audio spectrogram transformer, matching or outperforming FedAvg, Ditto, and local training approaches across multiple non-IID scenarios and in the presence of adversarial clients. Our results indicate that pFedMARL actively improves accuracy, robustness, and fairness, making it suitable for real-world deployments.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 26 Aug 2026.
Builds on
17 of 21 references.
References · 17
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2015Continuous control with deep reinforcement learningcited by 3,407
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
- 2015Prioritized Experience Replaycited by 1,099
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
- 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
- 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 305
- 2021SSAST: Self-Supervised Audio Spectrogram Transformercited by 169
- 2022MAE-AST: Masked Autoencoding Audio Spectrogram Transformercited by 82
- 2020Fast-Convergent Federated Learning with Adaptive Weightingcited by 67
5 more
- 2021ToyADMOS2: Another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditionscited by 26
- 2022MIMII DG: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection for Domain Generalization Taskcited by 23
- 2023CST-former: Transformer with Channel-Spectro-Temporal Attention for Sound Event Localization and Detectioncited by 8
- 2022FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learningcited by 7
- 2024FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learningcited by 6
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Optimized Local Updates in Federated Learning via Reinforcement Learning
- 2024On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations
- 2024CAESAR: Enhancing Federated RL in Heterogeneous MDPs through Convergence-Aware Sampling with Screening
- 2025Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning
- 2025Federated Reinforcement Learning in Heterogeneous Environments
- 2026FedGuide: Diffusion Prior Alignment and Value Baseline Guidance for Heterogeneous Federated Reinforcement Learning
- 2024Compressed Federated Reinforcement Learning with a Generative Model
- 2025A Survey of Multi Agent Reinforcement Learning: Federated Learning and Cooperative and Noncooperative Decentralized Regimes