Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition

TL;DR

This paper introduces CoLLA, a decentralized multi-agent lifelong learning algorithm that enables agents to share knowledge efficiently while preserving data privacy, outperforming existing distributed multi-task learning methods.

Contribution

The paper extends lifelong learning to a multi-agent network with a decentralized algorithm, providing theoretical guarantees and empirical improvements.

Findings

CoLLA outperforms existing distributed multi-task learning methods.

The algorithm maintains data privacy while sharing knowledge.

Theoretical guarantees ensure robust performance.

Abstract

Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience. Current lifelong learning algorithms rely upon a single learning agent that has centralized access to all data. In this paper, we extend the idea of lifelong learning from a single agent to a network of multiple agents that collectively learn a series of tasks. Each agent faces some (potentially unique) set of tasks; the key idea is that knowledge learned from these tasks may benefit other agents trying to learn different (but related) tasks. Our Collective Lifelong Learning Algorithm (CoLLA) provides an efficient way for a network of agents to share their learned knowledge in a distributed and decentralized manner, while preserving the privacy of the locally observed data. Note that a decentralized scheme is a subclass of distributed algorithms where a central server does not exist and in addition to data, computations are also distributed among the agents. We provide theoretical guarantees for robust performance of the algorithm and empirically demonstrate that CoLLA outperforms existing approaches for distributed multi-task learning on a variety of data sets.