BECAME: BayEsian Continual Learning with Adaptive Model MErging
This work addresses catastrophic forgetting in continual learning, offering a novel solution that improves task adaptation, though it appears incremental in its approach.
The paper tackles the stability-plasticity trade-off in continual learning by proposing BECAME, a framework that combines gradient projection with adaptive model merging based on Bayesian principles, achieving superior performance over state-of-the-art methods.
Continual Learning (CL) strives to learn incrementally across tasks while mitigating catastrophic forgetting. A key challenge in CL is balancing stability (retaining prior knowledge) and plasticity (learning new tasks). While representative gradient projection methods ensure stability, they often limit plasticity. Model merging techniques offer promising solutions, but prior methods typically rely on empirical assumptions and carefully selected hyperparameters. In this paper, we explore the potential of model merging to enhance the stability-plasticity trade-off, providing theoretical insights that underscore its benefits. Specifically, we reformulate the merging mechanism using Bayesian continual learning principles and derive a closed-form solution for the optimal merging coefficient that adapts to the diverse characteristics of tasks. To validate our approach, we introduce a two-stage framework named BECAME, which synergizes the expertise of gradient projection and adaptive merging. Extensive experiments show that our approach outperforms state-of-the-art CL methods and existing merging strategies.