Improving Mini-batch Optimal Transport via Partial Transportation
This addresses a specific issue in large-scale optimal transport for researchers and practitioners, but it is incremental as it builds on existing mini-batch methods.
The paper tackles the problem of misspecified mappings in mini-batch optimal transport (m-OT) by proposing mini-batch partial optimal transport (m-POT), which uses partial optimal transport to limit transported masses and reduce incorrect mappings. The result is favorable performance demonstrated in experiments on applications like deep domain adaptation and generative models.
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.