DPA4: 利用EMFA SO(2)卷积推动原子间势的精度-成本前沿
DPA4: Pushing the Accuracy-Cost Frontier of Interatomic Potentials with EMFA SO(2) Convolution
AI总结：
本文提出DPA4架构，通过EMFA SO(2)等变卷积和编译器友好的训练路径，在降低参数和训练成本的同时，在Matbench Discovery等基准上达到最优精度-成本平衡。
摘要：
机器学习原子间势现在在标准基准上接近量子力学精度，但最具表现力的等变架构的训练成本已成为严重瓶颈。我们引入了DPA4，一种SE(3)-等变原子间势架构，具有EMFA（边缘条件、多焦点、注意力）SO(2)-等变卷积，该卷积结合了低秩边缘-节点SO(2)-等变乘积、用于消息非线性的多焦点设计以及用于消息聚合的包络门控注意力。Lebedev网格投影进一步将非线性中的SO(3)-等变性保持到机器精度。编译器友好的保守能量梯度训练路径在torch.compile下提供了高达约3倍的挂钟加速。在合规的Matbench Discovery基准上，DPA4-Pro在排行榜上获得了最佳综合性能得分（CPS），而276万参数的DPA4-Air以10.9倍更少的参数和42.9倍更少的训练计算量，超过了3010万参数的eSEN-30M-MP基线的精度。在SPICE-MACE-OFF上，540万参数的DPA4-Plus将650万参数的eSEN基线的总分子能量和力误差分别降低了29%和30%，而270万参数的DPA4-Air仍然以约2.4倍更少的参数超越了该基线。这些结果共同将DPA4置于Matbench Discovery上新的精度-成本帕累托前沿，并使其成为未来多任务大型原子模型（LAM）预训练的有力候选骨干。
英文摘要：
Machine-learning interatomic potentials now approach quantum-mechanical accuracy, but the most expressive equivariant architectures are costly to evaluate, and the leading ones depend on auxiliary denoising or direct-force pretraining. We introduce DPA4, an SE(3)-equivariant architecture spanning six size classes from 0.48 to 25 million parameters and reaching the accuracy of the strongest published models at several-fold to an order-of-magnitude higher inference throughput. Its convolution couples edge and node features across all angular degrees in an edge-local frame, and its Wigner bilinear nonlinearity is universal in its full form and, on an exact quadrature grid, equivariant to machine precision. On Matbench Discovery, DPA4 leads every ranked metric, and every variant evaluated lies on the accuracy--throughput Pareto frontier of the compliant leaderboard. DPA4-Pro attains the lowest energy error on OMat24 and lower total-energy and force errors than the strongest conservative baseline on the OMol25 composition-validation split. All variants are trained through the conservative energy-gradient path alone, made practical by a threefold-faster compiled implementation. DPA4 thus brings leaderboard-class accuracy within the routine compute budgets of molecular-dynamics and materials-screening workflows, for both inorganic crystals and organic molecules.
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。
