MALOQ加速量子输运电子结构计算，支持超大规模原子系统预测。
MALOQ: Massively Accelerated Learning of Operators for Quantum Transport
- 基于旋转对称架构，设计高阶哈密顿矩阵专用数据处理核
- 训练效率提升30%以上，支持12,000原子系统推理
- 适合需要大规模电子结构模拟的研究者使用
机器学习（ML）算子模型可大幅降低密度泛函理论（DFT）哈密顿量/密度矩阵的计算成本，从而拓展电子结构计算至以往无法实现的规模。本文提出MALOQ（Massively Accelerated Learning of Operators for Quantum Transport），一个用于训练和预测包含少量至10万原子、采用大基组并涵盖多种元素系统的电子结构矩阵的应用。基于先进的SO(2)-等变骨干架构，MALOQ具备（i）处理高阶哈密顿矩阵数据的定制化数据处理核，以及（ii）可扩展的原子图边级分布式机制。在当前最大分子哈密顿量数据集上训练，相比分子级分布式框架，每轮训练时间减少超过30%，并支持任意尺寸材料图的推理。我们在Alps超级计算机上展示了3,000–12,000原子系统的可扩展训练与推理，分别使用最多192块和256块GPU。
原文摘要 · Abstract (English)
Machine-learned (ML) operator models can be trained to predict density functional theory (DFT) Hamiltonian/density matrices at significantly reduced computational cost, thus extending electronic-structure calculations to previously unfeasible scales. Here, we introduce MALOQ (Massively Accelerated Learning of Operators for Quantum Transport), an application built to train on and predict electronic-structure matrices for systems made of few to 100k atoms, described by large basis sets, and covering a wide range of atomic elements. Based on a state-of-the-art, SO(2)-equivariant backbone architecture, MALOQ provides (i) custom data-processing kernels to handle high-rank Hamiltonian matrix data and (ii) a scalable edge-wise distribution of atomic graph(s). Trained on the largest molecular Hamiltonian datasets available today, it reduces time-per-epoch by over 30% compared to a molecule-wise-distributed framework, and enables inference on material graphs of arbitrary size. We demonstrate scalable training and inference for 3,000-12,000 atoms on the Alps supercomputer, up to 192 GPUs and 256 GPUs, respectively.
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。