Populating memory in Continual Learning with Consistency Aware Sampling

Julio Hurtado, Alain Raymond, Vladimir Araujo, Vincenzo Lomonaco, Alvaro Soto, Davide Bacciu

Keywords: Continual Learning, Learning Consistency, Populating Memory, Memory-based Continual Learning

Abstract: Continual Learning (CL) methods aim to mitigate Catastrophic Forgetting (CF), where knowledge from previously learned tasks is often lost in favor of the new one. Among those algorithms, some have shown the relevance of keeping a rehearsal buffer with previously seen examples, referred to as $memory$. Yet, despite their popularity, limited research has been done to understand which elements are more beneficial to store in memory. It is common for this memory to be populated through random sampling, with little guiding principles that may aid in retaining prior knowledge. In this paper, and consistent with previous work, we found that some storage policies behave similarly given a certain memory size or compute budget, but when these constraints are relevant, results differ considerably. Based on these insights, we propose CAWS (Consistency AWare Sampling), an original storage policy that leverages a learning consistency score (C-Score) to populate the memory with elements that are $easy$ $to$ $learn$ and $representative$ of previous tasks. Because of the impracticality of directly using the C-Score in CL, we propose more feasible and efficient proxies to calculate the score that yield state-of-the-art results on CIFAR-100 and Tiny Imagenet.

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: General Machine Learning (ie none of the above)