Design Editing for Offline Model-based Optimization

TL;DR

This paper introduces DEMO, a novel offline model-based optimization method that uses diffusion priors to refine pseudo designs generated by gradient ascent, improving the validity and quality of optimized designs across various domains.

Contribution

DEMO is the first approach to incorporate diffusion priors for editing and refining pseudo design candidates in offline MBO, addressing out-of-distribution issues effectively.

Findings

DEMO achieves competitive scores on seven offline MBO tasks.

The diffusion-based editing process improves design validity.

Hyperparameter tuning is crucial for DEMO's performance.

Abstract

Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores. These tasks span various domains, such as robotics, material design, and protein and molecular engineering. A common approach involves training a surrogate model using existing designs and their corresponding scores, and then generating new designs through gradient-based updates with respect to the surrogate model. This method suffers from the out-of-distribution issue, where the surrogate model may erroneously predict high scores for unseen designs. To address this challenge, we introduce a novel method, Design Editing for Offline Model-based Optimization (DEMO), which leverages a diffusion prior to calibrate overly optimized designs. DEMO first generates pseudo design candidates by performing gradient ascent with respect to a surrogate model. While these pseudo design candidates contain information beyond the offline dataset, they might be invalid or have erroneously high predicted scores. Therefore, to address this challenge while utilizing the information provided by pseudo design candidates, we propose an editing process to refine these pseudo design candidates. We introduce noise to the pseudo design candidates and subsequently denoise them with a diffusion prior trained on the offline dataset, ensuring they align with the distribution of valid designs. Empirical evaluations on seven offline MBO tasks show that, with properly tuned hyperparameters, DEMOs score is competitive with the best previously reported scores in the literature.