提升原子图神经网络的跨域迁移能力，让小数据也能高效训练。
TriForces: Augmenting Atomistic GNNs for Transferable Representations
- 三流架构分离成分与结构信息，结合自监督学习保留可迁移表征
- 在2万样本下能量误差降低57%，力误差在各数据量级均优于基线
- 适合需要小样本迁移的材料模拟场景，尤其适合新体系快速建模
机器学习势函数（MLIP）在大规模密度泛函理论（DFT）数据上表现优异。但在实际应用中，常需用少量且昂贵的任务特定数据适配目标化学体系。然而，现有MLIP在不同领域间迁移性能不一，表征常丢失成分和结构信息。为此，我们提出TriForces——一种模型无关的三流框架，通过分离成分与结构信息，并结合自监督学习，有效保留可迁移表征。TriForces在MatBench和QM9上优于基线，无需DFT标签即可实现高性能；其学习的潜在空间支持高效相似结构检索。在OMat24数据集的有限数据训练下，仅使用2万样本时能量平均绝对误差（MAE）降低57%，且在不同样本规模下均提升了力预测的MAE。我们已将多种MLIP架构的预训练TriForces模型及代码开源至https://github.com/Ramlaoui/triforces。
原文摘要 · Abstract (English)
Machine learning interatomic potentials (MLIPs) achieve excellent accuracy when trained on large Density Functional Theory (DFT) data. To be useful in practice, they must often be adapted to target chemistries using small and expensive task-specific datasets. However, MLIPs transfer inconsistently across domains, with representations that often loose accessible composition and structure information. To address this, we present TriForces, a model-agnostic three-stream framework that separates composition and structure information, combined with self-supervised learning to preserve transferable representations. TriForces improves performance on MatBench and QM9 over baselines without needing DFT labels and enables efficient similar structure retrieval through its learned latent space. On OMat24, in limited-data training regime, TriForces reduces energy MAE by 57% at 20K samples only and improves force MAE across sample sizes. We release pretrained TriForces variants across multiple MLIP architectures with code at https://github.com/Ramlaoui/triforces.
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。