PXtal: Learning to Align Powder X-Ray Diffraction and Crystal Structures under Information Asymmetry across Modalities
Abstract
Scientific multimodal learning commonly assumes that paired views are comparably informative. Powder X-ray diffraction (PXRD) makes this mismatch explicit: compressing a three-dimensional crystal structure into a one-dimensional diffraction pattern loses information and makes the pattern harder to connect to the crystal structure that produced it. We introduce PXtal, a framework for learning aligned PXRD and crystal representations under this physically imposed information asymmetry. PXtal uses Unbalanced Optimal Transport (UOT) to adapt the cross-modal coupling and coupling-level generalized Kullback-Leibler (GKL) divergence to supervise the full transport plan. Across six test sets, including four zero-shot transfer sets, PXtal consistently outperforms the baseline models in PXRD-to-crystal candidate retrieval, with the largest gains when PXRD patterns have close but crystallographically distinct nonpaired neighbors, meaning similar input patterns associated with different crystals. The resulting crystal and PXRD encoders transfer more effectively to downstream materials and crystallographic tasks. These results identify information asymmetry as a general design problem in scientific multimodal learning: alignment objectives should reflect what each modality preserves.
Related
- Differentiable powder X-ray diffraction enables analysis of evolving structures
- PXRD-Bench: How Close Are We to Determining Crystal Structures from Powder Diffraction?
- Multiparameter Maximum Information States for Coherent Diffraction Measurements
- Spectral Information Content of Diffraction-Limited Images
- Learning materials spectra across modalities and scales with structure-conditioned neural fields
BibTeX
@misc{yang2026pxtal,
title = {{PXtal: Learning to Align Powder X-Ray Diffraction and Crystal Structures under Information Asymmetry across Modalities}},
author = {Zhuoran Yang and Christopher M. Collins and Bei Peng and Luke M. Daniels and Matthew J. Rosseinsky and Vladimir V. Gusev},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.10653},
eprint = {2610.10653},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.10653},
}
RIS
TY - UNPB
TI - PXtal: Learning to Align Powder X-Ray Diffraction and Crystal Structures under Information Asymmetry across Modalities
AU - Zhuoran Yang
AU - Christopher M. Collins
AU - Bei Peng
AU - Luke M. Daniels
AU - Matthew J. Rosseinsky
AU - Vladimir V. Gusev
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.10653
UR - https://arxiv.org/abs/2610.10653
AB - Scientific multimodal learning commonly assumes that paired views are comparably informative. Powder X-ray diffraction (PXRD) makes this mismatch explicit: compressing a three-dimensional crystal structure into a one-dimensional diffraction pattern loses information and makes the pattern harder to connect to the crystal structure that produced it. We introduce PXtal, a framework for learning aligned PXRD and crystal representations under this physically imposed information asymmetry. PXtal uses Unbalanced Optimal Transport (UOT) to adapt the cross-modal coupling and coupling-level generalized Kullback-Leibler (GKL) divergence to supervise the full transport plan. Across six test sets, including four zero-shot transfer sets, PXtal consistently outperforms the baseline models in PXRD-to-crystal candidate retrieval, with the largest gains when PXRD patterns have close but crystallographically distinct nonpaired neighbors, meaning similar input patterns associated with different crystals. The resulting crystal and PXRD encoders transfer more effectively to downstream materials and crystallographic tasks. These results identify information asymmetry as a general design problem in scientific multimodal learning: alignment objectives should reflect what each modality preserves.
ER -