CoCoL: A Communication Efficient Decentralized Collaborative Learning Method for Multi-Robot Systems

Collaborative learning enhances the performance and adaptability of multi-robot systems in complex tasks but faces significant challenges due to high communication overhead and data heterogeneity inherent in multi-robot tasks. To this end, we propose CoCoL, a Communication efficient decentralized Collaborative Learning method tailored for multi-robot systems with heterogeneous local datasets. Leveraging a mirror descent framework, CoCoL achieves remarkable communication efficiency with approximate Newton-type updates by capturing the similarity between objective functions of robots, and reduces computational costs through inexact sub-problem solutions. Furthermore, the integration of a gradient tracking scheme ensures its robustness against data heterogeneity. Experimental results on three representative multi-robot collaborative learning tasks show that the proposed CoCoL can significantly reduce both the number of communication rounds and total bandwidth consumption while maintaining state-of-the-art accuracy. These benefits are particularly evident in challenging scenarios involving non-IID (non-independent and identically distributed) data distribution, streaming data, and time-varying network topologies.

Authors

• Jiaxin Huang 0001
• Yan Huang 0036
• Yixian Zhao
• Wenchao Meng
• Jinming Xu 0002

Keywords

• Accuracy
• Simultaneous localization and mapping
• Quantization (signal)
• Federated learning
• Network topology
• Distributed databases
• Bandwidth
• Robustness
• Multi-robot systems
• Mirrors
• Efficient Communication
• Multi-agent Systems
• Collaborative Method
• Collaborative Learning Method
• Data Distribution
• Objective Function
• Total Consumption
• High Heterogeneity
• Learning Task
• Heterogeneous Data
• Data Streams
• Communication Overhead
• Local Dataset
• High Overhead
• Collaborative Tasks
• Total Bandwidth
• Communication Rounds
• Function Of The Robot
• Neural Network
• Computational Efficiency
• Local Updates
• Convex Objective Function
• Global Gradient
• Multi-agent Reinforcement Learning
• Proximal Policy Optimization
• Optimal Distribution
• Communication Graph
• Convex Function
• Object Location