Graph Learning and Order Parameters Reveal a Solid-to-Conformal Phase Transition in Skyrmion Lattices
By combining lattice-orientation order parameters with an unsupervised equivariant graph neural network (EGNN) and Gaussian mixture model (GMM), we identify the current-driven solid-to-conformal transition and autonomously classify local solid-like and conformal lattice states, providing a label-free route to phase identification in two-dimensional quasiparticle systems.
Recommended citation: W. Zhao, S. Lu, Q. Luo, G. Zhang, H. Lu, S. Fan, G. Zhao, J. Yang, Y. Hou, and L. Peng. Graph Learning and Order Parameters Reveal a Solid-to-Conformal Phase Transition in Skyrmion Lattices. Advanced Functional Materials, e78928 (2026). https://doi.org/10.1002/adfm.78928.
Download Paper
