PerCNet: Periodic Complete Representation for Crystal Graphs
Not on the map. Why?
Abstract (arXiv)
Crystal material representation is the foundation of crystal material research. Existing works consider crystal molecules as graph data with different representation methods and leverage the advantages of techniques in graph learning. A reasonable crystal representation method should capture the local and global information. However, existing methods only consider the local information of crystal molecules by modeling the bond distance and bond angle of first-order neighbors of atoms, which leads to the issue that different crystals will have the same representation. To solve this many-to-one issue, we consider the global information by further considering dihedral angles, which can guarantee that the proposed representation corresponds one-to-one with the crystal material. We first propose a periodic complete representation and calculation algorithm for infinite extended crystal materials. A theoretical proof for the representation that satisfies the periodic completeness is provided. Based on the proposed representation, we then propose a network for predicting crystal material properties, PerCNet, with a specially designed message passing mechanism. Extensive experiments are conducted on two real-world material benchmark datasets. The PerCNet achieves the best performance among baseline methods in terms of MAE. In addition, our results demonstrate the importance of the periodic scheme and completeness for crystal representation learning.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 51 references that are in the map. First posted on arXiv 3 Dec 2023.
Builds on
25 of 51 references.
References · 25
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
- 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
- 2020Directional Message Passing for Molecular Graphscited by 561
- 2019Graph U-Netscited by 492
- 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
- 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 270
- 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 255
13 more
- 2021Spherical Message Passing for 3D Graph Networkscited by 168
- 2020Building powerful and equivariant graph neural networks with structural message-passingcited by 97
- 2022Periodic Graph Transformers for Crystal Material Property Predictioncited by 87
- 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
- 2022ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphscited by 69
- 2021Rotation Invariant Graph Neural Networks using Spin Convolutionscited by 52
- 2020Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discoverycited by 46
- 2020Topology-Aware Graph Pooling Networkscited by 44
- 2023Efficient Approximations of Complete Interatomic Potentials for Crystal Property Predictioncited by 37
- 2022Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraintscited by 30
- 2020Deep Learning of High-Order Interactions for Protein Interface Predictioncited by 22
- 2021Geometric Transformers for Protein Interface Contact Predictioncited by 18
- 2022Multi-task Joint Strategies of Self-supervised Representation Learning on Biomedical Networks for Drug Discoverycited by 13
Built on by
Citing papers per year: 2025: 1.
1 paper.