Skip to content

Pformer: a plug-and-play periodicity-aware embedding for crystal property prediction

Sep 2026 · Machine Learning: Science and Technology · Vol 7 · 0 citations · 24 references
Physics

Abstract

Predicting macroscopic properties of crystalline materials from atomic structure remains a central challenge in computational materials science. We introduce Pformer, a modular crystal representation framework built around a Fourier-inspired source encoder. The source model is trained by supervised scalar-property regression from atom attributes and Cartesian coordinates; its Fourier analysis network (FAN) transformation applies sine, cosine, and GELU branches to learned latent projections before Transformer encoding. After source training, Pformer extracts the learned atom-embedding weight matrix, adapts its width when required, and uses it to initialize message-passing graph neural networks and transformer-based crystal encoders for downstream property prediction. We denote each initialized downstream variant as FAN-Backbone (e.g. FAN-PotNet); here FAN identifies the source-encoder component that produced the transferred weights, whereas Pformer denotes the complete transfer framework. On the Materials Project benchmark, FAN-PotNet reduces the bandgap mean absolute error (MAE) from 0.204 to 0.149 eV, and FAN-GATGNN lowers the shear modulus MAE from 0.075 to 0.022 log(GPa). On JARVIS-DFT, FAN-PotNet decreases the total energy MAE from 0.032 to 0.017 eV atom −1, and FAN-ComFormer improves the Ehull MAE from 0.048 to 0.045 eV. These benchmark comparisons show lower MAE for selected backbone–property combinations and ties for others, indicating that the effect of FAN-derived initialization depends on the downstream architecture and target property.

Read PDF

Similar papers

#artificial intelligence Preprint Sep 2026

uFlowCSP: Crystal Structure Prediction using Mean flow generative models

Crystal structure prediction (CSP) is fundamental to computational materials discovery. Generative models including CDVAE, DiffCSP, FlowMM, and CrystalFlow learn stable-crystal distributions directly, but diffusion and flow-matching inference requires tens to thousands of sequential network evaluations per candidate. W...

Sourin Dey, Dipannoy Das Gupta, Wei Lai et al. · 1 citation
Preprint Oct 2026

RipplePLM: Structural and Property Decoupling for Protein Mutation Effect Generation

Protein mutation effect generation asks a model to describe the functional consequence of a point mutation in natural language. Existing protein-to-text systems typically encode mutation information into undifferentiated representations, overlooking the organization of mutation-induced evidence across structural and bi...

Liuzhenghao Lv, Yu-Yang Liu, Yu-Yang Gao et al. · 0 citations
#machine learning Preprint Sep 2026

WEECFP-SuRGE: A Position-Aware Substructure Encoding Method for Molecular Property Prediction

This work introduces Wide Encoded Extended Connectivity Fingerprints with Substructure Rotary Graph-distance Encoding (SuRGE), a tokenized hierarchical Morgan representation in which graph-distance-dependent rotations are applied at the input and within transformer self-attention.

Robert W. Epps · 0 citations

Cross-Property Transfer Learning and Generative Crystal Design for Accelerated Discovery of Low-Thermal-Conductivity Materials.

Identifying crystalline materials with intrinsically low lattice thermal conductivity (κL) remains a major challenge in thermoelectric design due to complex phonon transport mechanisms and the limited availability of high-quality datasets. Although first-principles methods provide accurate κL predictions, their high co...

Harpriya Minhas, Rahul Kumar Sharma, Biswarup Pathak · 0 citations
Open access Oct 2026

Enhanced Generalization through Atomic Embeddings and Cross-Element Parameterization

The limited transferability of machine-learned interatomic potentials (MLIPs) to unseen chemical compositions constrains their utility in computational materials discovery. We present a systematic investigation into two interdependent design principleslearned atomic representations and cross-element parameterizationt...

M. Taleblou, Franco Pellegrini, Stefano de Gironcoli · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.