Unrolled Graph Learning for Multi-Agent Collaboration

TL;DR

This paper introduces an unrolled graph learning approach for multi-agent systems, enabling agents to autonomously identify collaborators and improve learning performance through adaptive, model-based collaboration graphs.

Contribution

The paper proposes a novel unrolled graph learning network that allows agents to dynamically learn and adapt their collaboration relationships based on model similarity.

Findings

Accurately identifies collaborative relationships among agents.

Significantly improves learning performance on regression and classification tasks.

Demonstrates effectiveness of adaptive collaboration in multi-agent learning.

Abstract

Multi-agent learning has gained increasing attention to tackle distributed machine learning scenarios under constrictions of data exchanging. However, existing multi-agent learning models usually consider data fusion under fixed and compulsory collaborative relations among agents, which is not as flexible and autonomous as human collaboration. To fill this gap, we propose a distributed multi-agent learning model inspired by human collaboration, in which the agents can autonomously detect suitable collaborators and refer to collaborators' model for better performance. To implement such adaptive collaboration, we use a collaboration graph to indicate the pairwise collaborative relation. The collaboration graph can be obtained by graph learning techniques based on model similarity between different agents. Since model similarity can not be formulated by a fixed graphical optimization, we design a graph learning network by unrolling, which can learn underlying similar features among potential collaborators. By testing on both regression and classification tasks, we validate that our proposed collaboration model can figure out accurate collaborative relationship and greatly improve agents' learning performance.