Online Continual Learning with Feedforward Adaptation

ABULIKEMU ABUDUWEILI, Changliu Liu

Keywords: Online adaptation, Online Learning, Continual Learning

Abstract:

Recently deep learning has been widely used in time-series prediction tasks. Although a trained deep neural network model typically performs well on the training set, performance drop significantly in a test set under slight distribution shifts. This challenge motivates the adoption of online adaptation algorithms to update the prediction models in real-time to improve the prediction performance. Existing online adaptation methods optimize the prediction model by feeding back the latest prediction error computed with respect to the latest observation. However, feedback based approach is prone to forgetting past information.
In this work, we propose an online adaptation method with feedforward compensation, which uses critical data samples from a memory buffer, instead of the latest samples, to optimize the prediction model. We prove that the proposed feedforward approach has a smaller error bound than the feedback approach in slow time-varying systems. The experiments on several time-series prediction tasks show that the proposed feedforward adaptation outperforms conventional feedback adaptation by more than 10%. In addition, the proposed feedforward adaptation method is able to estimate an uncertainty bound of the prediction that is agnostic from specific optimizers, while existing feedback adaptation could not.

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: Optimization (eg, convex and non-convex optimization)

TL;DR: We propose an online adaptation method with feedforward compensation.