Towards Accurate Test-Time Adaptation for Neural Surrogates

Anna Zimmel, Gianluca Galletti, Paul Setinek, Johannes Brandstetter, Werner Zellinger

Track: Track 1: Original Research/Position/Education/Attention Track

Keywords: Neural surrogates, Test-Time Adaptation, Distribution shift, Engineering Simulations

TL;DR: We propose a lightweight test-time adaptation approach that enables neural surrogates to adapt online to new engineering simulations without retraining.

Abstract: Neural surrogates that map input configurations (e.g., initial conditions and meshes) to simulation outputs are increasingly used in practical applications such as engineering design optimization. However, pre-trained models often experience significant performance drop on unseen problem configurations, such as different geometries, structural dimensions, and physical parameters. TTA mitigates distribution shifts by leveraging target configurations, online and at test-time. It avoids the need for costly re-training and doesn't require access to the original dataset, which is typically unavailable in practice. In this work we propose Representation Alignment for Simulations (SimRA), a novel method to improve performance at deployment, specific for multi-dimensional regression on simulation data. SimRA extends prior work on univariate regression [Adachi et al., ICLR 2025] with a novel feature weighting mechanism, ensuring stability in high-dimensional simulation settings. To our knowledge, this is the first study of TTA for neural surrogates. Empirical evaluations on diverse engineering tasks demonstrate strong performance and highlight the potential of TTA in the field.

Submission Number: 180