Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition
This work addresses the challenge of decentralized knowledge sharing among multiple agents in lifelong learning, which is incremental as it builds upon single-agent lifelong learning methods.
The paper tackles the problem of extending lifelong learning from a single agent to a network of multiple agents that collectively learn tasks, with the result that their Collective Lifelong Learning Algorithm (CoLLA) outperforms existing distributed multi-task learning approaches on various datasets.
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.