Radial Kernel Attention 提升聚合物机器学习力场的长程建模
Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields
一份聚合物力场的新注意力机制论文，5M 参数下能量误差砍掉 67%，还跟 Meta 的 UMA-S 直接对比了误差数据，做分子模拟的可以看看。
论文提出 Radial Kernel Attention（RKA），将原子到簇中心的距离映射为径向特征，以线性成本实现全局信息交换。在 OPoly26 验证集上，同参数量 5M 模型的 RKA 使每原子能量 MAE 降低 67.4%，力 MAE 降低 36.3%。20M 版本的 RKA 模型总能量 MAE 达 15.81 meV，力 MAE 为 2.619 meV/Å，对比对象是 UMA-S-1.2 与 UMA-S-1.2.1。模型在官方训练集上训练 12 个 epoch，通过微分包含径向坐标依赖的总能量得到保守力。
Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields
We introduce Radial Kernel Attention (RKA) for long-range modeling in polymer machine learning force fields. Local neighbor graphs constrain communication across polymer chains and their surrounding environments, while explicit all-pair attention incurs quadratic cost. RKA maps atomic distances from the cluster centroid to learned radial features and combines their overlap with content-dependent queries and keys. Factorized aggregation and readout enable global feature exchange at linear cost in atom count for fixed feature dimensions. We insert the invariant scalar update between EquiformerV3 local blocks and obtain conservative forces by differentiating the total energy, including its radial coordinate dependence. We evaluate energy and force prediction for finite polymer-derived clusters in OPoly26. Our models are trained on the official training split for 12 epochs and evaluated directly after training on the complete official validation split. A matched 5M comparison shows that RKA reduces per-atom energy and force MAEs by 67.4% and 36.3%, respectively. The 20M RKA model is compared with UMA-S-1.2 and UMA-S-1.2.1 on the same validation structures. The 20M model attains a total-energy MAE of 15.81 meV and a force MAE of 2.619 meV/angstrom; its per-atom energy MAE is 0.1182 meV/atom. RKA provides a compact global communication pathway that improves energy and force prediction on the evaluated polymer-derived clusters.