Pareto Actor-critic For Communication And Computation Co-optimization In Non-cooperative Federated Learning Services

Abstract

Federated learning (FL) in multi-service provider (SP) ecosystems is fundamentally hampered by non-cooperative dynamics, where privacy constraints and competing interests preclude the centralized optimization of multi-SP communication and computation resources. In this paper, we introduce PAC-MCoFL, a game-theoretic multi-agent reinforcement learning (MARL) framework where SPs act as agents to jointly optimize client assignment, adaptive quantization, and resource allocation. Within the framework, we integrate Pareto Actor-Critic (PAC) principles with expectile regression, enabling agents to conjecture optimal joint policies to achieve Pareto-optimal equilibria while modeling heterogeneous risk profiles. To manage the high-dimensional action space, we devise a ternary Cartesian decomposition (TCAD) mechanism that facilitates fine-grained control. Further, we develop PAC-MCoFL-p, a scalable variant featuring a parameterized conjecture generator that substantially reduces computational c

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytan2025pareto

Related papers

• Learning To Coordinate In Multi-agent Systems: A Coordinated Actor-critic Algorithm And Finite-time Guarantees (2021)0.00
• A Service-oriented Adaptive Hierarchical Incentive Mechanism For Federated Learning (2025)0.00
• PAC Guarantees For Cooperative Multi-agent Reinforcement Learning With Restricted Communication (2019)0.00
• F2A2: Flexible Fully-decentralized Approximate Actor-critic For Cooperative Multi-agent Reinforcement Learning (2020)0.00
• A Multi-agent Reinforcement Learning Approach For Efficient Client Selection In Federated Learning (2022)15.00
• PAC: Assisted Value Factorisation With Counterfactual Predictions In Multi-agent Reinforcement Learning (2022)0.00
• Small-scale-fading-aware Resource Allocation In Wireless Federated Learning (2025)0.00
• Communication-efficient Actor-critic Methods For Homogeneous Markov Games (2022)0.00