Neural architectures that learn potential energy surfaces from molecular data have undergone fast improvement in recent years. A key driver of this success is the Message Passing Neural Network (MPNN) paradigm. Its favorable scaling with system size partly relies upon a spatial distance limit on messages. While this focus on locality is a useful inductive bias, it also impedes the learning of long-range interactions such as electrostatics and van der Waals forces. To address this drawback, we propose Ewald message passing: a nonlocal Fourier space scheme which limits interactions via a cutoff on frequency instead of distance, and is theoretically well-founded in the Ewald summation method. It can serve as an augmentation on top of existing MPNN architectures as it is computationally cheap and agnostic to other architectural details. We test the approach with four baseline models and two datasets containing diverse periodic (OC20) and aperiodic structures (OE62). We observe robust improvements in energy mean absolute errors across all models and datasets, averaging 10% on OC20 and 16% on OE62. Our analysis shows an outsize impact of these improvements on structures with high long-range contributions to the ground truth energy.

翻译：近年来，从分子数据学习势能面的神经架构取得了快速发展。这一成功的关键驱动力是消息传递神经网络（MPNN）范式。该系统尺寸的有利缩放部分依赖于消息的空间距离限制。虽然这种局部性偏好是一种有用的归纳偏置，但它也阻碍了静电相互作用和范德瓦尔斯力等长程相互作用的学习。为解决这一缺陷，我们提出埃瓦尔德消息传递：一种非局域傅里叶空间方案，通过频率截断而非距离来限制相互作用，并在理论上以埃瓦尔德求和法为基础。该方法计算成本低廉且不依赖于其他架构细节，可作为现有MPNN架构的增强模块。我们使用四个基线模型以及包含周期性结构（OC20）和非周期性结构（OE62）的两个数据集进行测试。在所有模型和数据集上，能量平均绝对误差均出现稳健改进，在OC20上平均降低10%，在OE62上平均降低16%。分析表明，这些改进对真实能量中长程贡献占比高的结构影响尤为显著。