Geodesic-Aligned Gradient Projection for Continual Task Learning

Abstract

Deep networks notoriously suffer from performance deterioration on previous tasks when learning from sequential tasks, i.e., catastrophic forgetting. Recent methods of gradient projection show that the forgetting is resulted from the gradient interference on old tasks and accordingly propose to update the network in an orthogonal direction to the task space. However, these methods assume the task space is invariant and neglect the gradual change between tasks, resulting in sub-optimal gradient projection and a compromise of the continual learning capacity. To tackle this problem, we propose to embed each task subspace into a non-Euclidean manifold, which can naturally capture the change of tasks since the manifold is intrinsically non-static compared to the Euclidean space. Subsequently, we analytically derive the accumulated projection between any two subspaces on the manifold along the geodesic path by integrating an infinite number of intermediate subspaces. Building upon this derivation, we propose a novel geodesic-aligned gradient projection (GAGP) method that harnesses the accumulated projection to mitigate catastrophic forgetting. The proposed method utilizes the geometric structure information on the task manifold by capturing the gradual change between the new and the old tasks. Empirical studies on image classification demonstrate that the proposed method alleviates catastrophic forgetting and achieves on-par or better performance compared to the state-of-the-art approaches.