IBCL: Zero-shot Model Generation under Stability-Plasticity Trade-offs

TMLR Paper5010 Authors

Abstract: Algorithms that balance the stability-plasticity trade-off are well studied in the Continual Learning literature. However, only a few focus on obtaining models for specified trade-off preferences. When solving the problem of continual learning under specific trade-offs (CLuST), state-of-the-art techniques leverage rehearsal-based learning, which requires retraining when a model corresponding to a new trade-off preference is requested. This is inefficient, since there potentially exist a significant number of different trade-offs, and a large number of models may be requested. As a response, we propose Imprecise Bayesian Continual Learning (IBCL), an algorithm that tackles CLuST efficiently. IBCL replaces retraining with a constant-time convex combination. Given a new task, IBCL (1) updates the knowledge base as a convex hull of model parameter distributions, and (2) generates one Pareto-optimal model per given trade-off via convex combination without additional training. That is, obtaining models corresponding to specified trade-offs via IBCL is zero-shot. Experiments whose baselines are current CLuST algorithms show that IBCL improves by at most 45% on average per task accuracy, and by 43% on peak per task accuracy while maintaining a near-zero to positive backward transfer. In addition, its training overhead, measured by the number of batch updates, remains constant at every task, regardless of the number of preferences requested. Details can be found at: https://github.com/ibcl-anon/ibcl.

Submission Length: Long submission (more than 12 pages of main content)

Assigned Action Editor: ~Cedric_Archambeau1

Submission Number: 5010