Distributed Continual Learning
This addresses the challenge of combining continual and federated learning for distributed agents, though it appears incremental as it builds on existing paradigms with new algorithms and insights.
This paper tackles the problem of distributed continual learning where independent agents face unique tasks and incrementally develop and share knowledge, finding that modular parameter sharing yields the best performance while minimizing communication costs.
This work studies the intersection of continual and federated learning, in which independent agents face unique tasks in their environments and incrementally develop and share knowledge. We introduce a mathematical framework capturing the essential aspects of distributed continual learning, including agent model and statistical heterogeneity, continual distribution shift, network topology, and communication constraints. Operating on the thesis that distributed continual learning enhances individual agent performance over single-agent learning, we identify three modes of information exchange: data instances, full model parameters, and modular (partial) model parameters. We develop algorithms for each sharing mode and conduct extensive empirical investigations across various datasets, topology structures, and communication limits. Our findings reveal three key insights: sharing parameters is more efficient than sharing data as tasks become more complex; modular parameter sharing yields the best performance while minimizing communication costs; and combining sharing modes can cumulatively improve performance.