Constraint-Aware Flow Matching via Randomized Exploration

TL;DR

This paper introduces new constraint-aware flow matching methods that improve constraint satisfaction in generative models, applicable with differentiable distances or query-based constraint sets, demonstrated through synthetic and adversarial example generation.

Contribution

It proposes novel flow matching techniques that handle constraints via distance penalties or randomized learning, significantly enhancing constraint satisfaction in generative models.

Findings

Proposed methods outperform vanilla models in constraint satisfaction.

Two-stage approach is more computationally efficient than one-stage.

Effective in generating adversarial examples with black-box classifiers.

Abstract

We consider the problem of designing constraint-aware flow matching (FM) models that address the issue of constraint violations commonly observed in vanilla generative models. We consider two scenarios, viz.: (a) when a differentiable distance function to the constraint set is given, and (b) when the constraint set is only available via queries to a membership oracle. For case (a), we propose a simple adaptation of the FM objective with an additional term that penalizes the distance between the constraint set and the generated samples. For case (b), we propose to employ randomization and learn a mean flow that is numerically shown to have a high likelihood of satisfying the constraints. This approach deviates significantly from existing works that require simple convex constraints, knowledge of a barrier function, or a reflection mechanism to constrain the probability flow. Furthermore, in the proposed setting we show that a two-stage approach, where both stages approximate the same original flow but with only the second stage probing the constraints via randomization, is more computationally efficient than the corresponding one-stage approach. Through several synthetic cases of constrained generation, we numerically show that the proposed approaches achieve significant gains in terms of constraint satisfaction while matching the target distributions. As a showcase for a practical oracle-based constraint, we show how our approach can be used for training an adversarial example generator, using queries to a hard-label black-box classifier. We conclude with several future research directions. Our code is available at https://github.com/ZhengyanHuan/FM-RE.