MALOQ: Massively Accelerated Learning of Operators for Quantum Transport
This work addresses the computational bottleneck of electronic-structure calculations for materials science, enabling scalable ML-based predictions for large systems.
MALOQ introduces a massively accelerated framework for learning DFT Hamiltonian/density matrices, achieving over 30% reduction in training time per epoch compared to molecule-wise distribution and enabling inference on material graphs of arbitrary size, demonstrated on up to 12,000 atoms using 256 GPUs.
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.