Relation-Aware Slicing in Cross-Domain Alignment

TL;DR

This paper introduces a relation-aware, optimization-free slicing distribution for the Sliced Gromov-Wasserstein distance, improving computational efficiency and alignment performance through a novel pairwise association capturing method.

Contribution

It proposes the Relation-Aware Projecting Direction (RAPD) and Relation-Aware Slicing Distribution (RASD), enabling faster sampling and better alignment without optimization overhead.

Findings

RASGW and variants outperform SGW in alignment tasks.

The new method reduces computational costs significantly.

Empirical results demonstrate improved accuracy and efficiency.

Abstract

The Sliced Gromov-Wasserstein (SGW) distance, aiming to relieve the computational cost of solving a non-convex quadratic program that is the Gromov-Wasserstein distance, utilizes projecting directions sampled uniformly from unit hyperspheres. This slicing mechanism incurs unnecessary computational costs due to uninformative directions, which also affects the representative power of the distance. However, finding a more appropriate distribution over the projecting directions (slicing distribution) is often an optimization problem in itself that comes with its own computational cost. In addition, with more intricate distributions, the sampling itself may be expensive. As a remedy, we propose an optimization-free slicing distribution that provides fast sampling for the Monte Carlo approximation. We do so by introducing the Relation-Aware Projecting Direction (RAPD), effectively capturing the pairwise association of each of two pairs of random vectors, each following their ambient law. This enables us to derive the Relation-Aware Slicing Distribution (RASD), a location-scale law corresponding to sampled RAPDs. Finally, we introduce the RASGW distance and its variants, e.g., IWRASGW (Importance Weighted RASGW), which overcome the shortcomings experienced by SGW. We theoretically analyze its properties and substantiate its empirical prowess using extensive experiments on various alignment tasks.