A Materials Foundation Model via Hybrid Invariant-Equivariant Architectures
This work addresses a key design problem in materials science for researchers developing MLIPs, offering an incremental improvement by combining existing architectural approaches.
The paper tackled the trade-off between invariant and equivariant architectures in machine learning interatomic potentials (MLIPs) by proposing HIENet, a hybrid model that integrates both types of layers while satisfying physical constraints, achieving state-of-the-art performance with significant computational speedups.
Machine learning interatomic potentials (MLIPs) can predict energy, force, and stress of materials and enable a wide range of downstream discovery tasks. A key design choice in MLIPs involves the trade-off between invariant and equivariant architectures. Invariant models offer computational efficiency but may not perform as well, especially when predicting high-order outputs. In contrast, equivariant models can capture high-order symmetries, but are computationally expensive. In this work, we propose HIENet, a hybrid invariant-equivariant materials interatomic potential model that integrates both invariant and equivariant message passing layers, while provably satisfying key physical constraints. HIENet achieves state-of-the-art performance with considerable computational speedups over prior models. Experimental results on both common benchmarks and downstream materials discovery tasks demonstrate the efficiency and effectiveness of HIENet.