通过物理约束的位置预测，提升分子表示学习的准确性与泛化能力
Equivariant Masked Position Prediction for Efficient Molecular Representation
- 基于分子势能与受力理论设计等变位置预测任务
- 在多个基准数据集上超越现有自监督方法，性能显著提升
- 适合需要高精度分子表征的药物发现与材料设计场景
图神经网络（GNNs）在计算化学领域展现出巨大潜力。然而，分子数据的有限性引发了人们对GNN能否有效捕捉物理与化学基本原理的担忧，限制了其泛化能力。为应对这一挑战，我们提出一种新型自监督方法——等变掩码位置预测（EMPP），其基于分子内势能与力理论。与传统属性掩码方法不同，EMPP构建了一个更精确的位置预测任务，有助于学习量子力学特征。该方法避免了去噪方法中常用的高斯混合分布近似，从而更准确地获取物理性质。实验结果表明，EMPP显著提升了先进分子架构的性能，超越了当前最先进的自监督方法。代码已公开于 https://github.com/ajy112/EMPP。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) have shown considerable promise in computational chemistry. However, the limited availability of molecular data raises concerns regarding GNNs' ability to effectively capture the fundamental principles of physics and chemistry, which constrains their generalization capabilities. To address this challenge, we introduce a novel self-supervised approach termed Equivariant Masked Position Prediction (EMPP), grounded in intramolecular potential and force theory. Unlike conventional attribute masking techniques, EMPP formulates a nuanced position prediction task that is more well-defined and enhances the learning of quantum mechanical features. EMPP also bypasses the approximation of the Gaussian mixture distribution commonly used in denoising methods, allowing for more accurate acquisition of physical properties. Experimental results indicate that EMPP significantly enhances performance of advanced molecular architectures, surpassing state-of-the-art self-supervised approaches. Our code is released in https://github.com/ajy112/EMPP
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。