AI RESEARCH
Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data
arXiv CS.AI
•
ArXi:2604.15380v1 Announce Type: cross We present an exascale workflow for materials discovery using atomistic graph foundation models built on HydraGNN. We jointly train on 16 open first-principles datasets (544+ million structures covering 85+ elements) using a multi-task architecture with per-dataset heads and a scalable ADIOS2/DD data pipeline. On Frontier, we execute six large-scale DeepHyper hyperparameter optimization campaigns in FP64 and promote the top-performing message-passing models to sustained 2,048-node.