arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.01801cs.LGcs.AIphysics.comp-ph
收藏

一种用于几何建模的量子启发式神经网络

A quatum inspired neural network for geometric modeling

Chinese Academy of Sciences(中国科学院);Huawei Technologies Ltd(华为技术有限公司);Université de Montréal(蒙特利尔大学)

Weitao Du, Shengchao Liu, Xuecang Zhang

AI总结:

针对现有几何GNN仅能实现多体系统平均场近似、难以捕捉复杂关联的问题,提出基于等变矩阵乘积态的消息传递策略,可高效建模多体关联并保留对称性,在基准任务上取得更优精度,为首款参数化几何张量网络。

摘要:

通过将物理系统视为3D多体点云,几何图神经网络(GNN),例如SE(3)/E(3)等变GNN,已展现出可观的性能。尤其是其高效的消息传递机制,使其擅长建模分子和晶体材料。然而,当前的几何GNN仅能提供多体系统的平均场近似,且该近似封装在两体消息传递中,因此无法捕捉这些几何图内的复杂关联。为解决这一局限,学界引入了张量网络——这类网络在计算物理学中被广泛用于通过高阶张量处理多体系统。但将这些张量化网络集成到GNN的消息传递框架中,面临可扩展性和对称性守恒(例如置换和旋转)方面的挑战。对此,我们提出了一种创新的基于等变矩阵乘积态(MPS)的消息传递策略,实现了张量收缩运算的高效执行。我们的方法可有效建模复杂的多体关联,抑制平均场近似,并捕捉几何图内的对称性。重要的是,它可无缝替代几何GNN固有的标准消息传递和层聚合模块。我们在包括经典牛顿系统预测和量子张量哈密顿矩阵预测在内的基准任务上,通过实验验证了该方法的优越准确性。据我们所知,该方法是参数化几何张量网络的首次应用。

英文摘要:

By conceiving physical systems as 3D many-body point clouds, geometric graph neural networks (GNNs), such as SE(3)/E(3) equivalent GNNs, have showcased promising performance. In particular, their effective message-passing mechanics make them adept at modeling molecules and crystalline materials. However, current geometric GNNs only offer a mean-field approximation of the many-body system, encapsulated within two-body message passing, thus falling short in capturing intricate relationships within these geometric graphs. To address this limitation, tensor networks, widely employed by computational physics to handle manybody systems using high-order tensors, have been introduced. Nevertheless, integrating these tensorized networks into the message-passing framework of GNNs faces scalability and symmetry conservation (e.g., permutation and rotation) challenges. In response, we introduce an innovative equivariant Matrix Product State (MPS)-based message-passing strategy, through achieving an efficient implementation of the tensor contraction operation. Our method effectively models complex many-body relationships, suppressing mean-field approximations, and captures symmetries within geometric graphs. Importantly, it seamlessly replaces the standard message-passing and layer-aggregation modules intrinsic to geometric GNNs. We empirically validate the superior accuracy of our approach on benchmark tasks, including predicting classical Newton systems and quantum tensor Hamiltonian matrices. To our knowledge, our approach represents the inaugural utilization of parameterized geometric tensor networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑