Achieving Plasticity-Stability Trade-Off in Continual Learning Through Adaptive Orthogonal Projection

Catastrophic forgetting is the crucial challenge for continual learning. One of the state-of-the-art approaches is the orthogonal projection, which aims to learn each task by updating model parameters in the direction orthogonal to the subspace spanned by the previous task input. Although such strict orthogonal weight constraints ensure no interference with tasks that have been learned to achieve model stability, they greatly sacrifice model plasticity. In this paper, we propose an adaptive balanced orthogonal projection (AdaBOP) method, to search for the optimal network parameter updating direction to address the plasticity-stability dilemma in continual learning. The proposed AdaBOP method can adaptively adjust its tendency towards plasticity-stability trade-off based on the layer-wise feature space correlations of the model between old and new tasks. To further improve the training efficiency, we also implement the AdaBOP method in the uncentered covariance matrix space of the previous tasks, and finally achieve a better stability-plasticity trade-off in continual learning efficiently. Experimental results greatly demonstrate the effectiveness of the proposed method, which achieves superior performances to state-of-the-art continual learning approaches. The code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/hyscn/AdaBOP</uri>.