Keywords: Distribution shift, Continual learning, Domain Adaptation, Semi-supervised learning, Model drift, Online learning, Benchmark
TL;DR: We introduce the novel OCL-PDS problem for studying gradual distribution shift with time, and release 4 new benchmarks and 12 algorithms/baselines implementation for this new problem.
Abstract: We introduce the novel OCL-PDS problem - Online Continual Learning for Progressive Distribution Shift. PDS refers to the subtle, gradual, and continuous distribution shift that widely exists in modern deep learning applications. It is widely observed in industry that PDS can cause significant performance drop. While previous work in continual learning and domain adaptation addresses this problem to some extent, our investigations from the practitioner's perspective reveal flawed assumptions that limit their applicability on daily challenges faced in real-world scenarios, and this work aims to close the gap between academic research and industry. For this new problem, we build 4 new benchmarks from the Wilds dataset, and implement 12 algorithms and baselines including both supervised and semi-supervised methods, which we test extensively on the new benchmarks. We hope that this work can provide practitioners with tools to better handle realistic PDS, and help scientists design better OCL algorithms.
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: Infrastructure (eg, datasets, competitions, implementations, libraries)
Supplementary Material: zip