用更少算力训练出高性能材料基础模型，兼顾精度与速度。
Training a Foundation Model for Materials on a Budget
- 采用简化NequIP结构结合等变归一化与Muon优化器
- 仅需100 A100 GPU小时，训练成本低20倍
- 推理速度比顶尖模型快100倍，适合资源有限团队
材料建模的基础模型发展迅速，但训练成本高昂，多数研究组难以负担。我们提出Nequix，一种参数量70万的E(3)等变势能模型，通过简化NequIP设计并结合等变均方根层归一化与Muon优化器，在保持精度的同时显著降低计算需求。Nequix在Matbench-Discovery和MDR Phonon基准上排名第三，训练仅耗时100 A100 GPU小时，相比多数方法节省20倍成本，且推理速度比当前最优模型快两个数量级。模型权重与可复现代码已开源至https://github.com/atomicarchitects/nequix。
原文摘要 · Abstract (English)
Foundation models for materials modeling are advancing quickly, but their training remains expensive, often placing state-of-the-art methods out of reach for many research groups. We introduce Nequix, a compact E(3)-equivariant potential that pairs a simplified NequIP design with modern training practices, including equivariant root-mean-square layer normalization and the Muon optimizer, to retain accuracy while substantially reducing compute requirements. Nequix has 700K parameters and was trained in 100 A100 GPU-hours. On the Matbench-Discovery and MDR Phonon benchmarks, Nequix ranks third overall while requiring a 20 times lower training cost than most other methods, and it delivers two orders of magnitude faster inference speed than the current top-ranked model. We release model weights and fully reproducible codebase at https://github.com/atomicarchitects/nequix.
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。