Timezone: »

Algorithm Selection for Deep Active Learning with Imbalanced Datasets
Jifan Zhang · Shuai Shao · Saurabh Verma · Robert Nowak

Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep networks, but the empirical performance of active learningalgorithms can vary dramatically across datasets and applications. It is difficult to know in advance which active learning strategy will perform well or best in a given application. To address this, we propose the first adaptive algorithm selection strategy for deep active learning. For any unlabeled dataset, our (meta) algorithm TAILOR (Thompson ActIve Learning algORithm selection) iteratively and adaptively chooses among a set of candidate active learning algorithms. TAILOR uses novel reward functions aimed at gathering class-balanced examples. Extensiveexperiments in multi-class and multi-label applications demonstrate TAILOR ’s effectiveness in achieving accuracy comparable or better than that of the best of the candidate algorithms.

Author Information

Jifan Zhang (University of Wisconsin)
Shuai Shao (Meta)
Saurabh Verma (Meta)
Robert Nowak (University of Wisconsion-Madison)
Robert Nowak

Robert Nowak holds the Nosbusch Professorship in Engineering at the University of Wisconsin-Madison, where his research focuses on signal processing, machine learning, optimization, and statistics.

More from the Same Authors