ED-DiT：用于从电子密度学习可迁移分子表示的物理引导扩散预训练
ED-DiT: Physics-Guided Diffusion Pretraining for Transferable Molecular Representations from Electron Density
AI总结：
本研究提出ED-DiT，一种物理引导的扩散Transformer，通过电子密度点云自监督预训练学习可迁移分子表示，在6项EDBench任务及低监督场景下均优于基线，展现出良好效果。
AI中文摘要：
预训练在学习可迁移表示方面展现出强大潜力，但基于电子密度的分子学习领域仍未得到充分探索。电子密度提供了分子电子结构的连续三维描述，同时捕捉局部空间模式和全局物理量。这引发了一个关键问题：电子密度场能否用于自监督预训练，以学习在各类电子结构相关任务间迁移的共享表示？本文提出ED-DiT，一种用于电子密度点云自监督预训练的物理引导扩散Transformer。ED-DiT通过在不同扩散噪声水平下重建受损和部分掩码的对数密度场来学习可复用表示，还引入电子数一致性约束以保持总电子质量。预训练后的编码器可适配属性预测、开/闭壳分类、分子-电子密度检索以及分子条件下的电子密度预测任务。在6项EDBench任务上的实验表明，ED-DiT的表现始终优于从头训练的相同架构，尤其在监督数据有限的情况下优势显著；在分子条件电子密度预测任务中，其将均方根误差（RMSE）从2.2474降至1.3753，超越现有基线；仅使用10%标签时，其将轨道能量预测的RMSE从0.0293降至0.0138。这些结果证明了物理引导的电子密度预训练在学习可迁移分子表示方面的有效性。
英文摘要：
Pretraining has shown strong potential for learning transferable representations, yet it remains underexplored for electron-density-based molecular learning. Electron density provides a continuous three-dimensional description of molecular electronic structure, capturing both local spatial patterns and global physical quantities. This raises a key question: can electron-density fields be used for self-supervised pretraining to learn a shared representation that transfers across diverse electronic-structure-related tasks? We propose ED-DiT, a physics-guided Diffusion Transformer for self-supervised pretraining on electron-density point clouds. ED-DiT learns reusable representations by reconstructing corrupted and partially masked log-density fields across diffusion noise levels. An electron-number consistency constraint is further introduced to preserve the total electronic mass. The pretrained encoder can be adapted to property prediction, open-/closed-shell classification, molecule-electron-density retrieval, and molecule-conditioned electron-density prediction. Experiments on six EDBench tasks show that ED-DiT consistently outperforms the same architecture trained from scratch, especially under limited supervision. For molecule-conditioned electron-density prediction, it reduces RMSE from 2.2474 to 1.3753 and surpasses the available baseline. With only 10% labels, it improves orbital energy prediction RMSE from 0.0293 to 0.0138. These results demonstrate the effectiveness of physics-guided electron-density pretraining for learning transferable molecular representations.
