Few-shot Molecular Property Prediction via Hierarchically Structured Learning on Relation Graphs

• Published in: Neural networks Vol. 163; pp. 122 - 131
• Main Authors: Ju, Wei, Liu, Zequn, Qin, Yifang, Feng, Bin, Wang, Chen, Guo, Zhihui, Luo, Xiao, Zhang, Ming
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2023
• Subjects: Algorithms; Benchmarking; Drug Discovery; Few-shot learning; Graph neural networks; Knowledge; Meta learning; Molecular property prediction; Neural Networks, Computer; Graph neural networks; Molecular property prediction; Few-shot learning; Meta learning
• ISSN: 0893-6080; 1879-2782
• DOI: 10.1016/j.neunet.2023.03.034

This paper studies few-shot molecular property prediction, which is a fundamental problem in cheminformatics and drug discovery. More recently, graph neural network based model has gradually become the theme of molecular property prediction. However, there is a natural deficiency for existing methods, that is, the scarcity of molecules with desired properties, which makes it hard to build an effective predictive model. In this paper, we propose a novel framework called Hierarchically Structured Learning on Relation Graphs (HSL-RG) for molecular property prediction, which explores the structural semantics of a molecule from both global-level and local-level granularities. Technically, we first leverage graph kernels to construct relation graphs to globally communicate molecular structural knowledge from neighboring molecules and then design self-supervised learning signals of structure optimization to locally learn transformation-invariant representations from molecules themselves. Moreover, we propose a task-adaptive meta-learning algorithm to provide meta knowledge customization for different tasks in few-shot scenarios. Experiments on multiple real-life benchmark datasets show that HSL-RG is superior to existing state-of-the-art approaches. •This paper studies an important task: few-shot molecular property prediction.•We model the molecular structural semantics from global- and local-level views.•Global-level view constructs relation graphs to communicate neighbor knowledge.•Local-level view achieves transformation invariance from molecules themselves.•Experiments on the benchmarks verify the superiority of the proposed approach.