Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios

Xueying Zhan, Zeyu Dai, Qingzhong Wang, Haoyi Xiong, Dejing Dou, Qing Li, Antoni B. Chan

Keywords: active learning, pareto optimization, out-of-distribution

Abstract: Pool-based Active Learning (AL) has achieved great success in minimizing labeling costs by sequentially selecting the most informative unlabeled samples from a large unlabeled data pool and querying their labels from oracle/annotators. However, existing AL sampling schemes might not work well under out-of-distribution (OOD) data scenarios, where the unlabeled data pool contains data samples that do not belong to the pre-defined categories of the target task. Achieving good AL performance under OOD data scenarios is a challenging task due to the natural conflict between AL sampling strategies and OOD sample detection -- both more informative in-distribution (ID) data and OOD data in unlabeled data pool may be assigned high informativeness scores (e.g., high entropy) during AL processes. In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with \emph{fixed batch size} from the unlabeled data pool. We cast the AL sampling task as a multi-objective optimization problem and utilize Pareto optimization based on two conflicting objectives: (1) the typical AL sampling scheme (e.g., maximum entropy), and (2) the confidence of not being an OOD data sample. Experimental results show the effectiveness of our POAL on classical Machine Learning (ML) and Deep Learning (DL) tasks.

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)