ElectrolyteFM：通过跨属性知识学习统一电解质属性预测
ElectrolyteFM: Unifying Electrolyte Property Prediction through Cross-Property Knowledge Learning
- VoltaAI
- Renmin University of China（中国人民大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对电解质属性预测中孤立学习忽略可迁移信息、无差别共享引发干扰的问题，提出统一模型ElectrolyteFM，通过属性特定表示与专家池跨属性知识路由及残差适配，在Electrolyte12上平均误差降低14.8%，并泛化至未见数据集。
AI中文摘要：
电解质配方设计需要平衡多种物理化学属性，然而现有模型往往只关注有限的属性子集。孤立地学习每个属性可能会忽略可迁移的化学信息，而无差别地共享信息则可能引入跨属性干扰。我们的定向迁移分析表明，联合学习两个属性预测任务相对于单独训练可能提升或降低预测性能，且任务之间存在不对称的迁移效应。我们提出了ElectrolyteFM，一个统一的多属性预测模型，通过有效识别和利用属性特定特征以及跨属性共享知识，能够更准确地预测每种电解质的多个属性。具体而言，ElectrolyteFM独立学习属性特定表示，并通过一个单独训练的专家池捕获跨属性知识。一个路由器为每种配方和目标属性选择相关的共享信息，属性特定的残差适配器将这些信息转换为对相应表示的修正以进行预测。在Electrolyte12上的实验表明，相对于最强的电解质特定基线，ElectrolyteFM将12种电解质属性的平均归一化平均绝对误差降低了14.8%。在一个训练期间未见过的独立钠电解质数据集上，相对于表现最佳的基线，它将电导率平均绝对误差降低了6.7%。
英文摘要：
Electrolyte formulation design requires balancing multiple physicochemical properties, yet existing models often focus on a limited subset. Learning each property in isolation can overlook transferable chemical information, whereas indiscriminate sharing can introduce cross-property interference. Our directed transfer analysis shows that jointly learning two property prediction tasks can improve or degrade prediction relative to separate training, with asymmetric transfer effects between the tasks. We propose ElectrolyteFM, a unified multi-property prediction model which can more accurately predict multiple properties of each electrolyte by effectively identifying and utilizing property-specific features and knowledge shared across properties. More specifically, ElectrolyteFM learns property-specific representations independently and captures cross-property knowledge through a separately trained expert pool. A router selects relevant shared information for each formulation and target property, and property-specific residual adapters convert this information into corrections to the corresponding representation for prediction. Experiments on Electrolyte12 show that ElectrolyteFM reduces normalized mean absolute error averaged across 12 electrolyte properties by 14.8% relative to the strongest electrolyte-specific baseline. On an independent sodium-electrolyte dataset unseen during training, it reduces conductivity mean absolute error by 6.7% relative to the best-performing baseline.
