Neural Unbalanced Optimal Transport via Cycle-Consistent Semi-Couplings
This addresses the challenge of unbalanced scenarios in optimal transport for applications like single-cell biology, where mass conservation is violated, offering a domain-specific solution.
The paper tackled the problem of comparing unpaired samples when mass is not conserved, such as in single-cell biology where population size changes due to cell proliferation or death, by introducing NubOT, a neural unbalanced optimal transport method using semi-couplings, which yielded notable improvements over previous neural OT methods in forecasting cancer cell line responses to drugs.
Comparing unpaired samples of a distribution or population taken at different points in time is a fundamental task in many application domains where measuring populations is destructive and cannot be done repeatedly on the same sample, such as in single-cell biology. Optimal transport (OT) can solve this challenge by learning an optimal coupling of samples across distributions from unpaired data. However, the usual formulation of OT assumes conservation of mass, which is violated in unbalanced scenarios in which the population size changes (e.g., cell proliferation or death) between measurements. In this work, we introduce NubOT, a neural unbalanced OT formulation that relies on the formalism of semi-couplings to account for creation and destruction of mass. To estimate such semi-couplings and generalize out-of-sample, we derive an efficient parameterization based on neural optimal transport maps and propose a novel algorithmic scheme through a cycle-consistent training procedure. We apply our method to the challenging task of forecasting heterogeneous responses of multiple cancer cell lines to various drugs, where we observe that by accurately modeling cell proliferation and death, our method yields notable improvements over previous neural optimal transport methods.