南阳师范学院学报2026，Vol.25Issue(3)：40-47,8.
基于知识蒸馏的分子性质预测及其可扩展性分析
Molecular Property Prediction Based on Knowledge Distillation and Its Scalability Analysis
摘要
Abstract
Knowledge distillation maintains predictive accuracy while reducing computational costs by transferring knowledge from complex teacher models to streamlined student models.This paper constructs a knowledge distil-lation framework based on a multi-task weighted optimization loss function specifically for molecular property pre-diction tasks.Using three graph neural network models,namely SchNet,DimeNet++,and TensorNet,the effectiveness of the framework in both domain-specific and cross-domain knowledge distillation settings was inves-tigated systematically.In the domain-specific scenario,teacher models trained on the QM9 dataset guide student models in predicting unseen quantum mechanical properties within the same dataset,verifying the potential of the proposed method for enhancing precision and efficiency.In the cross-domain scenarios,knowledge distillation is employed to transfer QM9-pretrained teacher embeddings to experimental datasets such as ESOL(solubility)and FreeSolv(hydration free energy),the predictive accuracy of the proposed method in cross-domain,small-sample training environments was demonstraed.The results indicate that knowledge distillation is a robust strategy for en-hancing molecular representation learning,providing critical technical support for the core requirements of high precision and low computational cost in materials science and drug discovery.关键词
知识蒸馏/图神经网络/分子性质预测/跨领域迁移Key words
knowledge distillation/graph neural networks/molecular property prediction/cross-domain transfer分类
信息技术与安全科学引用本文复制引用
李宝磊,刘祥,刘琨,游文涛,赵紫威,孟军霞..基于知识蒸馏的分子性质预测及其可扩展性分析[J].南阳师范学院学报,2026,25(3):40-47,8.基金项目
国家自然科学基金青年项目"有序层状/无序岩盐富锂锰基正极材料精准构筑及锰电化学活性机理研究"(52202220) （52202220）
江西省教育厅科技项目"面向材料设计的模型辅助多目标优化方法研究"(GJJ2501104). （GJJ2501104）
