ReGNet: Reciprocal Space-Aware Long-Range Modeling and Multi-Property Prediction for Crystals

• URL: http://arxiv.org/abs/2502.02748v1
• Date: Tue, 04 Feb 2025 22:31:39 GMT
• Title: ReGNet: Reciprocal Space-Aware Long-Range Modeling and Multi-Property Prediction for Crystals
• Authors: Jianan Nie, Peiyao Xiao, Kaiyi Ji, Peng Gao,
• Abstract summary: We introduce Reciprocal Geometry Network (ReGNet), a novel architecture that integrates geometric GNNs and reciprocal blocks to model short-range and long-range interactions.<n>We also introduce ReGNet-MT, a multi-task extension that employs mixture of experts (MoE) for multi-property prediction.
• Score: 18.68276260557569
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predicting properties of crystals from their structures is a fundamental yet challenging task in materials science. Unlike molecules, crystal structures exhibit infinite periodic arrangements of atoms, requiring methods capable of capturing both local and global information effectively. However, most current works fall short of capturing long-range interactions within periodic structures. To address this limitation, we leverage reciprocal space to efficiently encode long-range interactions with learnable filters within Fourier transforms. We introduce Reciprocal Geometry Network (ReGNet), a novel architecture that integrates geometric GNNs and reciprocal blocks to model short-range and long-range interactions, respectively. Additionally, we introduce ReGNet-MT, a multi-task extension that employs mixture of experts (MoE) for multi-property prediction. Experimental results on the JARVIS and Materials Project benchmarks demonstrate that ReGNet achieves significant performance improvements. Moreover, ReGNet-MT attains state-of-the-art results on two bandgap properties due to positive transfer, while maintaining high computational efficiency. These findings highlight the potential of our model as a scalable and accurate solution for crystal property prediction. The code will be released upon paper acceptance.

Related papers

• RelGNN: Composite Message Passing for Relational Deep Learning [56.48834369525997]
  We introduce RelGNN, a novel GNN framework specifically designed to capture the unique characteristics of relational databases. At the core of our approach is the introduction of atomic routes, which are sequences of nodes forming high-order tripartite structures. RelGNN consistently achieves state-of-the-art accuracy with up to 25% improvement.
  arXiv  Detail & Related papers  (2025-02-10T18:58:40Z)
• EffiCANet: Efficient Time Series Forecasting with Convolutional Attention [12.784289506021265]
  EffiCANet is designed to enhance forecasting accuracy while maintaining computational efficiency. EffiCANet achieves the maximum reduction of 10.02% in MAE over state-of-the-art models.
  arXiv  Detail & Related papers  (2024-11-07T12:54:42Z)
• Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs [66.98487644676906]
  We introduce Neural P$3$M, a versatile enhancer of geometric GNNs to expand the scope of their capabilities. It exhibits flexibility across a wide range of molecular systems and demonstrates remarkable accuracy in predicting energies and forces. It also achieves an average improvement of 22% on the OE62 dataset while integrating with various architectures.
  arXiv  Detail & Related papers  (2024-09-26T08:16:59Z)
• TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
  We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
  arXiv  Detail & Related papers  (2024-04-15T06:01:48Z)
• Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding [10.170537065646323]
  Predicting physical properties of materials from their crystal structures is a fundamental problem in materials science. We show that crystal structures are infinitely repeating, periodic arrangements of atoms, whose fully connected attention results in infinitely connected attention. We propose a simple yet effective Transformer-based encoder architecture for crystal structures called Crystalformer.
  arXiv  Detail & Related papers  (2024-03-18T11:37:42Z)
• ADA-GNN: Atom-Distance-Angle Graph Neural Network for Crystal Material Property Prediction [3.7050297294650716]
  Property prediction is a fundamental task in crystal material research. Bond angles and bond distances are two key structural information that greatly influence crystal properties. We propose a novel Atom-Distance-Angle Graph Neural Network (ADA-GNN) for property prediction tasks.
  arXiv  Detail & Related papers  (2024-01-22T09:03:16Z)
• Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale [54.15522908057831]
  We propose an adapted version of the computationally-Mixer for STTD forecast at scale. Our results surprisingly show that this simple-yeteffective solution can rival SOTA baselines when tested on several traffic benchmarks. Our findings contribute to the exploration of simple-yet-effective models for real-world STTD forecasting.
  arXiv  Detail & Related papers  (2023-07-04T05:19:19Z)
• Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting [52.47493322446537]
  We develop a adaptive, interpretable and scalable forecasting framework, which seeks to individually model each component of the spatial-temporal patterns. SCNN works with a pre-defined generative process of MTS, which arithmetically characterizes the latent structure of the spatial-temporal patterns. Extensive experiments are conducted to demonstrate that SCNN can achieve superior performance over state-of-the-art models on three real-world datasets.
  arXiv  Detail & Related papers  (2023-05-22T13:39:44Z)
• Predicting Oxide Glass Properties with Low Complexity Neural Network and Physical and Chemical Descriptors [1.8734449181723827]
  We present a low complexity neural network (LCNN) that provides improved performance in predicting the properties of oxide glasses. By training on a large dataset (50000) of glass components, we show the LCNN outperforms state-of-the-art algorithms such as XGBoost. We demonstrate the universality of the LCNN models by predicting the properties for glasses with new components that were not present in the original training set.
  arXiv  Detail & Related papers  (2022-10-19T12:23:30Z)
• Global Filter Networks for Image Classification [90.81352483076323]
  We present a conceptually simple yet computationally efficient architecture that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness.
  arXiv  Detail & Related papers  (2021-07-01T17:58:16Z)
• A Universal Framework for Featurization of Atomistic Systems [0.0]
  Reactive force fields based on physics or machine learning can be used to bridge the gap in time and length scales. We introduce the Gaussian multi-pole (GMP) featurization scheme that utilizes physically-relevant multi-pole expansions of the electron density around atoms. We demonstrate that GMP-based models can achieve chemical accuracy for the QM9 dataset, and their accuracy remains reasonable even when extrapolating to new elements.
  arXiv  Detail & Related papers  (2021-02-04T03:11:00Z)
• When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks [57.0502745301132]
  We propose Micro-Dense Nets, a novel architecture with global residual learning and local micro-dense aggregations. Our micro-dense block can be integrated with neural architecture search based models to boost their performance.
  arXiv  Detail & Related papers  (2020-04-19T08:34:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.