Integral Continual Learning Along the Tangent Vector Field of Tasks
This work addresses catastrophic forgetting for machine learning systems that need to learn from sequential data, offering an incremental improvement over existing replay-based methods.
The paper tackles the problem of catastrophic forgetting in continual learning by proposing a lightweight method that integrates information along the tangent vector field of tasks, achieving performance improvements of 18.77% and 28.48% on Seq-CIFAR-10 and Seq-TinyImageNet, respectively, with a memory buffer as low as 0.4% of source datasets.
We propose a lightweight continual learning method which incorporates information from specialized datasets incrementally, by integrating it along the vector field of "generalist" models. The tangent plane to the specialist model acts as a generalist guide and avoids the kind of over-fitting that leads to catastrophic forgetting, while exploiting the convexity of the optimization landscape in the tangent plane. It maintains a small fixed-size memory buffer, as low as 0.4% of the source datasets, which is updated by simple resampling. Our method achieves strong performance across various buffer sizes for different datasets. Specifically, in the class-incremental setting we outperform the existing methods that do not require distillation by an average of 18.77% and 28.48%, for Seq-CIFAR-10 and Seq-TinyImageNet respectively. Our method can easily be used in conjunction with existing replay-based continual learning methods. When memory buffer constraints are relaxed to allow storage of metadata such as logits, we attain an error reduction of 17.84% towards the paragon performance on Seq-CIFAR-10.