Continual Learning In Low-coherence Subspace: A Strategy To Mitigate Learning Capacity Degradation

Zihao Xu, Zhengyu Li, Yufei Shi, Xihao Wang, Yingjie Liu, Kexin Ke, Xian Wei

Keywords: oblique manifold, continual learning, learning capacity degradation, catastrophic forgetting, low-coherence, orthogonal projection

TL;DR: This paper contributes a novel method in continual learning, called Low-coherence Subspaces Projection (LcSP), which solves both the catastrophic forgetting problem and the learning capacity degradation problem.

Abstract: Methods using gradient orthogonal projection, an efficient strategy in continual learning, have achieved promising success in mitigating catastrophic forgetting. However, these methods often suffer from the learning capacity degradation problem following the increasing number of tasks. To address this problem, we propose to learn new tasks in low-coherence subspaces rather than orthogonal subspaces. Specifically, we construct a unified cost function involving regular DNN parameters and gradient projections on the Oblique manifold. We finally develop a gradient descent algorithm on a smooth manifold to jointly minimize the cost function and minimize both the inter-task and the intra-task coherence. Numerical experimental results show that the proposed method has prominent advantages in maintaining the learning capacity when tasks are increased, especially on a large number of tasks, compared with baselines.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning