Low-Budget Active Learning through Entropic Optimal Transport

The paper introduces a low-budget active learning approach that selects a small coreset of data points for training high-accuracy models, particularly useful when labeling is expensive, such as in medical contexts. It uses features from a pretrained self-supervised model and applies entropic optimal transport—specifically the Sinkhorn divergence—as the selection criterion, enabling dimension-free sample complexity and efficient gradient-based optimization. The method combines gradient-based candidate generation with a swap-based local search, achieving superior performance over existing heuristics on image and medical datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• benchmarks