Abstract:Unlike most static material properties widely studied in the machine learning literature, ionic transport properties are inherently dynamic, making their fast and accurate prediction from static atomic structures challenging. The current standard approach, molecular dynamics (MD) simulations, suffers from prohibitively high computational cost. Recent autoregressive learning-based MD acceleration methods requiring sequential inference remain slow and prone to error accumulation; in contrast, existing non-autoregressive material property prediction models are less accurate because they fail to exploit dynamics. Moreover, existing methods typically benefit from datasets either with or without atomic trajectories, but not both. To overcome these limitations, we propose a non-autoregressive learning framework based on auxiliary modality learning, which treats atomic trajectories as an auxiliary modality during training but does not require them at inference. This enables the predictor to learn dynamics without sequential inference while benefiting from both types of datasets. As a result, our framework achieves over 200 times speedup compared to autoregressive models on the dataset with atomic trajectories while substantially reducing prediction error relative to non-autoregressive benchmarks across both types of datasets. Our code is available at this https URL.
| Comments: | International Conference on Machine Learning (ICML 2026) (to appear) (Please cite our conference version.) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Atomic Physics (physics.atom-ph); Chemical Physics (physics.chem-ph); Computational Physics (physics.comp-ph) |
| Cite as: | arXiv:2605.09311 [cs.LG] |
| (or arXiv:2605.09311v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.09311 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Won-Yong Shin [view email]
[v1]
Sun, 10 May 2026 04:09:01 UTC (589 KB)