2021/08/22 by Khai T. Nguyen, Nguyen, Khai, Dang Nguyen +6 · 4 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Image Enhancement Techniques #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM
paper · pdf · doi:10.48550/arxiv.2108.09645
openalex publication_date 2021/08/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Mini-batch optimal transport (m-OT) has been widely used recently to deal with the memory issue of OT in large-scale applications. Despite their practicality, m-OT suffers from misspecified mappings, namely, mappings that are optimal on the mini-batch level but are partially wrong in the comparison with the optimal transportation plan between the original measures. Motivated by the misspecified mappings issue, we propose a novel mini-batch method by using partial optimal transport (POT) between mini-batch empirical measures, which we refer to as mini-batch partial optimal transport (m-POT). Leveraging the insight from the partial transportation, we explain the source of misspecified mappings from the m-OT and motivate why limiting the amount of transported masses among mini-batches via POT can alleviate the incorrect mappings. Finally, we carry out extensive experiments on various applications such as deep domain adaptation, partial domain adaptation, deep generative model, color transfer, and gradient flow to demonstrate the favorable performance of m-POT compared to current mini-batch methods.