Dif-MAML: Decentralized Multi-Agent Meta-Learning

TL;DR

Dif-MAML introduces a decentralized multi-agent meta-learning algorithm that enables agents to collaboratively learn and adapt to new tasks efficiently, overcoming resource and communication limitations of centralized systems.

Contribution

The paper proposes a novel fully-decentralized multi-agent meta-learning algorithm, Dif-MAML, with theoretical convergence guarantees and improved scalability over traditional methods.

Findings

Agents reach agreement at a linear rate

Convergence to stationary points in non-convex environments

Superior performance in simulations compared to non-cooperative approaches

Abstract

The objective of meta-learning is to exploit the knowledge obtained from observed tasks to improve adaptation to unseen tasks. As such, meta-learners are able to generalize better when they are trained with a larger number of observed tasks and with a larger amount of data per task. Given the amount of resources that are needed, it is generally difficult to expect the tasks, their respective data, and the necessary computational capacity to be available at a single central location. It is more natural to encounter situations where these resources are spread across several agents connected by some graph topology. The formalism of meta-learning is actually well-suited to this decentralized setting, where the learner would be able to benefit from information and computational power spread across the agents. Motivated by this observation, in this work, we propose a cooperative fully-decentralized multi-agent meta-learning algorithm, referred to as Diffusion-based MAML or Dif-MAML. Decentralized optimization algorithms are superior to centralized implementations in terms of scalability, avoidance of communication bottlenecks, and privacy guarantees. The work provides a detailed theoretical analysis to show that the proposed strategy allows a collection of agents to attain agreement at a linear rate and to converge to a stationary point of the aggregate MAML objective even in non-convex environments. Simulation results illustrate the theoretical findings and the superior performance relative to the traditional non-cooperative setting.