Improving Multi-task GNNs for Molecular Property Prediction via Missing Label Imputation

作     者：Fenyu Hu Dingshuo Chen Qiang Liu Shu Wu Fenyu Hu;Dingshuo Chen;Qiang Liu;Shu Wu

作者机构：University of Chinese Academy of SciencesBeijing100190China Center for Research on Intelligent Perception and ComputingState Key Laboratory of Multimodal Artificial Intelligence SystemsInstitute of AutomationChinese Academy of SciencesBeijing100190China 

出 版 物：《Machine Intelligence Research》 (机器智能研究(英文版))

年 卷 期：2025年第22卷第1期

页      面：131-144页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(Nos.62141608 and U19B 2038) the CAAI Huawei MindSpore Open Fund 

主　　题：Graph classification imbalance learning prediction bias mixture of experts multiview representations 

摘      要：The prediction of molecular properties is a fundamental task in the field of drug ***,graph neural networks(GNNs)have been gaining prominence in this *** a molecule tends to have multiple correlated properties,there is a great need to develop the multi-task learning ability of ***,limited by expensive and time-consuming human annotations,collecting complete labels for each task is *** a result,most existing benchmarks involve many missing labels in training data,and the performance of GNNs is impaired due to the lack of sufficient supervision *** overcome this obstacle,we propose to improve multi-task molecular property prediction by missing label ***,a bipartite graph is first introduced to model the molecule-task co-occurrence ***,the imputation of missing labels is transformed into predicting missing edges on this bipartite *** predict the missing edges,a graph neural network is devised,which can learn the complex molecule-task co-occurrence *** that,we select reliable pseudo labels according to the uncertainty of the prediction *** with enough and reliable supervision information,our approach achieves state-of-the-art performance on a variety of real-world datasets.