发表机构
LIT AI Lab; Institute for Machine Learning; JKU Linz（LIT人工智能实验室; 机器学习研究所; 约翰开普勒大学林茨分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ParetoTransport，一种免训练的流匹配引导方法，通过Wasserstein匹配迭代输运离线分布至帕累托前沿，控制分布位移与质量分配，在标准离线多目标优化基准上取得最先进性能。
AI 中文摘要
离线多目标优化不仅需要将候选设计的客观向量移向帕累托前沿，还需要沿前沿有效地分布它们。生成方法最近成为一种自然的方法，因为它们学习可行设计的分布，同时允许生成过程被引导至有前景的设计。然而，现有方法大多保留经典的样本级引导策略，使得生成方法的分布级建模能力未被充分利用。我们提出ParetoTransport，一种针对预训练流匹配模型的免训练引导方法，它明确指定并细化目标空间中的群体级分布。ParetoTransport引导流匹配采样器迭代地将经验离线分布输运至帕累托前沿，并通过Wasserstein匹配中间代理分布。这直接控制了沿前沿的分布位移和质量分配。我们建立了收敛性结果，并在标准离线MOO基准上展示了最先进的性能，将近期评估从超体积扩展到世代距离、倒置世代距离和Wasserstein距离。
英文摘要
Offline multi-objective optimization requires not only moving the objective vectors of candidate designs toward the Pareto front, but also distributing them effectively along it. Generative methods have recently emerged as a natural approach because they learn a distribution over feasible designs while allowing generation to be steered toward promising designs. Existing methods, however, largely retain classical sample-wise guidance strategies, leaving the distribution-level modeling capability of generative methods underused. We propose ParetoTransport, a training-free guidance method for pre-trained flow-matching models that explicitly specifies and refines a population-level distribution in objective space. ParetoTransport guides a flow-matching sampler to iteratively transport the empirical offline distribution toward the Pareto front, with Wasserstein matching to intermediate proxy distributions. This directly controls distributional displacement and mass allocation along the front. We establish a convergence result and demonstrate state-of-the-art performance on standard offline MOO benchmarks, extending recent evaluations beyond hypervolume to generational distance, inverted generational distance, and Wasserstein distance.
