MiSAL: Active Learning for Every Budget

Guy Hacohen, Daphna Weinshall

Keywords: Deep Active learning, Low budget, High budget, Deep learning

TL;DR: Different budget sizes call for different active learning strategies; we introduce a practical method to determine in advance which strategy should be used and when.

Abstract: In supervised Active Learning (AL), the learner can manipulate the labeled training set by choosing examples to be labeled by an oracle. The size of the labeled set is termed budget. Recent years have seen significant progress in this domain in the context of deep active learning. In particular, it has been shown that in general, different families of AL strategies are suitable for high and low budgets. Here we address for the first time the problem of deciding which family of strategies is most suitable for a given budget in a given task. We start from the theoretical analysis of a mixture model, which motivates a computational approach to decide on the most suitable family of methods for the task and budget at hand. We then propose a practical decision algorithm, which determines what family of strategies should be preferred. Using this algorithm, we introduce MiSAL - a mixed strategy active learning algorithm. MiSAL combines AL strategies from different families, resulting in a method that fits all budgets. We support the analysis by an empirical study, showing the superiority of our method when dealing with image datasets.

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