XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction
Abstract
Multiphase powder X-ray diffraction (PXRD) analysis remains a fundamental bottleneck in structure identification, as real-world synthesis often produces complex mixtures whose constituent phases (components) cannot be reliably disentangled. While recent advances in representation-based crystal retrieval and generation suggest the possibility of inferring structures directly from PXRD, existing approaches largely assume single-phase inputs and break down in multiphase settings. Here, we present XDecomposer, a prior-free framework for joint decomposition and identification of multiphase XRD patterns without requiring candidate phase lists, structural templates, or prior knowledge of phase number. We formulate multiphase diffraction analysis as a set prediction problem, where the model infers an unordered set of phase-resolved components, their mixture proportions, and corresponding structural representations within a unified architecture. A phase-query-driven decomposition mechanism, together with diffraction-consistent physical reconstruction, enables accurate source separation while preserving crystallographic fidelity. Extensive experiments on both simulated and experimental datasets show that XDecomposer substantially improves reconstruction accuracy and phase identification across diverse chemical systems, while maintaining strong generalization to unseen mixtures. These results provide a practical route toward data-driven, source-resolved multiphase XRD analysis and reduce long-standing dependence on prior-guided iteratively phase matching. The code is openly available at https://github.com/Licht0812/XDecomposer
Related
- Scalable machine learning framework for multiphase identification from powder X-ray diffraction
- Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows
- PoreML: A Data-Driven Framework for Learning Multiphase Flow in Porous Media
- Machine learning magnetic interactions from neutron powder diffraction data
- PXtal: Learning to Align Powder X-Ray Diffraction and Crystal Structures under Information Asymmetry across Modalities
BibTeX
@misc{gao2026xdecomposer,
title = {{XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction}},
author = {Hanyu Gao and Bin Cao and Yunyue Su and Tong-Yi Zhang and Qiang Liu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.05866},
eprint = {2605.05866},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.05866},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction
AU - Hanyu Gao
AU - Bin Cao
AU - Yunyue Su
AU - Tong-Yi Zhang
AU - Qiang Liu
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2605.05866
UR - https://arxiv.org/abs/2605.05866
AB - Multiphase powder X-ray diffraction (PXRD) analysis remains a fundamental bottleneck in structure identification, as real-world synthesis often produces complex mixtures whose constituent phases (components) cannot be reliably disentangled. While recent advances in representation-based crystal retrieval and generation suggest the possibility of inferring structures directly from PXRD, existing approaches largely assume single-phase inputs and break down in multiphase settings. Here, we present XDecomposer, a prior-free framework for joint decomposition and identification of multiphase XRD patterns without requiring candidate phase lists, structural templates, or prior knowledge of phase number. We formulate multiphase diffraction analysis as a set prediction problem, where the model infers an unordered set of phase-resolved components, their mixture proportions, and corresponding structural representations within a unified architecture. A phase-query-driven decomposition mechanism, together with diffraction-consistent physical reconstruction, enables accurate source separation while preserving crystallographic fidelity. Extensive experiments on both simulated and experimental datasets show that XDecomposer substantially improves reconstruction accuracy and phase identification across diverse chemical systems, while maintaining strong generalization to unseen mixtures. These results provide a practical route toward data-driven, source-resolved multiphase XRD analysis and reduce long-standing dependence on prior-guided iteratively phase matching. The code is openly available at https://github.com/Licht0812/XDecomposer
ER -