PuSH - Publikationsserver des Helmholtz Zentrums München

Yashas, A. ; Belakaria, S.* ; Ermon, S.* ; Bauer, S. ; Engelhardt, B.*

Preference-Guided Diffusion for Multi-Objective Offline Optimization.

In: (39th Conference on Neural Information Processing Systems, NeurIPS 2025, 02-07 December 2025, San Diego). 2025. 17774-17797 (Advances in Neural Information Processing Systems ; 38)
Offline multi-objective optimization aims to identify Pareto-optimal solutions given a dataset of designs and their objective values. In this work, we propose a preference-guided diffusion model that generates Pareto-optimal designs by leveraging a classifier-based guidance mechanism. Our guidance classifier is a preference model trained to predict the probability that one design dominates another, directing the diffusion model toward optimal regions of the design space. Crucially, this preference model generalizes beyond the training distribution, enabling the discovery of Pareto-optimal solutions outside the observed dataset. We introduce a novel diversity-aware preference guidance, augmenting Pareto dominance preference with diversity criteria. This ensures that generated solutions are optimal and well-distributed across the objective space, a capability absent in prior generative methods for offline multi-objective optimization. We evaluate our approach on various continuous offline multi-objective optimization tasks and find that it consistently outperforms other inverse/generative approaches while remaining competitive with forward/surrogate-based optimization methods. Our results highlight the effectiveness of classifier-guided diffusion models in generating diverse and high-quality solutions that approximate the Pareto front well.
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
ISSN (print) / ISBN 1049-5258
Konferenztitel 39th Conference on Neural Information Processing Systems, NeurIPS 2025
Konferzenzdatum 02-07 December 2025
Konferenzort San Diego
Quellenangaben Band: 38, Heft: , Seiten: 17774-17797 Artikelnummer: , Supplement: ,
Institut(e) Helmholtz Artificial Intelligence Cooperation Unit (HAI)