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

2025-08-28

AI Summary

To address high communication overhead and performance degradation caused by data heterogeneity—particularly non-IID distributions—in multi-robot collaborative learning, this paper proposes a decentralized efficient collaborative learning framework. Methodologically, it integrates mirror descent with gradient tracking: mirror descent enables approximate Newton-type updates to capture similarity among robots’ objective functions; inexact subproblem solving reduces computational complexity; and gradient tracking enhances robustness against non-IID data, streaming inputs, and time-varying communication topologies. Experiments across three representative multi-robot tasks demonstrate that the method significantly reduces both the number of communication rounds and total bandwidth consumption (average reduction >40%), while maintaining state-of-the-art accuracy. Its advantages are especially pronounced under challenging conditions—including severe non-IID data distributions and dynamic network topologies.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Machine Learning: Distributed Machine Learning & Federated Learning
• Multiagent Systems: Multiagent Learning

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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 the superiority of the proposed CoCoL in significantly reducing 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.

Problem

• Reducing communication overhead in multi-robot collaborative learning
• Addressing data heterogeneity in decentralized robot systems
• Improving efficiency in non-IID streaming data scenarios

Innovation

• Decentralized collaborative learning with mirror descent
• Approximate Newton updates for communication efficiency
• Gradient tracking scheme against data heterogeneity