ParetoFlow: Guided Flows in Multi-Objective Optimization

TL;DR

ParetoFlow introduces a flow-based generative approach guided by a multi-objective predictor to efficiently approximate Pareto fronts in offline multi-objective optimization, outperforming existing methods.

Contribution

It presents a novel flow matching method with multi-objective predictor guidance and local filtering, advancing generative modeling in offline multi-objective optimization.

Findings

Achieves state-of-the-art performance on multiple tasks.

Effectively guides sample generation towards the Pareto front.

Introduces a neighboring evolution module for improved diversity.

Abstract

In offline multi-objective optimization (MOO), we leverage an offline dataset of designs and their associated labels to simultaneously minimize multiple objectives. This setting more closely mirrors complex real-world problems compared to single-objective optimization. Recent works mainly employ evolutionary algorithms and Bayesian optimization, with limited attention given to the generative modeling capabilities inherent in such data. In this study, we explore generative modeling in offline MOO through flow matching, noted for its effectiveness and efficiency. We introduce ParetoFlow, specifically designed to guide flow sampling to approximate the Pareto front. Traditional predictor (classifier) guidance is inadequate for this purpose because it models only a single objective. In response, we propose a multi-objective predictor guidance module that assigns each sample a weight vector, representing a weighted distribution across multiple objective predictions. A local filtering scheme is introduced to address non-convex Pareto fronts. These weights uniformly cover the entire objective space, effectively directing sample generation towards the Pareto front. Since distributions with similar weights tend to generate similar samples, we introduce a neighboring evolution module to foster knowledge sharing among neighboring distributions. This module generates offspring from these distributions, and selects the most promising one for the next iteration. Our method achieves state-of-the-art performance across various tasks.