Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs

Meyer Scetbon, Gabriel Peyré, marco cuturi

Keywords: Optimal Transport, Gromov-Wasserstein, Low-rank methods

TL;DR: We introduce a new approach to solve the GW problem, getting the best of a low rank constraint on the coupling (GW's optimization variable) and a low rank factorization of the cost matrices (GW's data).

Abstract: The ability to compare and align related datasets living in heterogeneous spaces plays an increasingly important role in machine learning. The Gromov-Wasserstein (GW) formalism can help tackle this problem. Its main goal is to seek an assignment (more generally a coupling matrix) that can register points across otherwise incomparable datasets. As a non-convex and quadratic generalization of optimal transport (OT), GW is NP-hard. Yet, heuristics are known to work reasonably well in practice, the state of the art approach being to solve a sequence of nested regularized OT problems. While popular, that heuristic remains too costly to scale, with cubic complexity in the number of samples $n$. We show in this paper how a recent variant of the Sinkhorn algorithm can substantially speed up the resolution of GW. That variant restricts the set of admissible couplings to those admitting a low rank factorization as the product of two sub-couplings. By updating alternatively each sub-coupling, our algorithm computes a stationary point of the problem in quadratic time with respect to the number of samples. When cost matrices have themselves low rank, our algorithm has time complexity $\mathcal{O}(n)$. We demonstrate the efficiency of our method on simulated and real data.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/linear-time-gromov-wasserstein-distances/code)