Few-Shot Graph Learning for Molecular Property Prediction
This addresses the challenge of predicting new molecular properties with scarce data, which is common in drug discovery, but it is incremental as it builds on existing graph neural network and meta-learning techniques.
The paper tackles the problem of molecular property prediction with limited experimental data by proposing Meta-MGNN, a few-shot learning model that incorporates self-supervised modules and task weights, and it outperforms state-of-the-art methods on two public datasets.
The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery. The existing deep neural network methods usually require large training dataset for each property, impairing their performances in cases (especially for new molecular properties) with a limited amount of experimental data, which are common in real situations. To this end, we propose Meta-MGNN, a novel model for few-shot molecular property prediction. Meta-MGNN applies molecular graph neural network to learn molecular representation and builds a meta-learning framework for model optimization. To exploit unlabeled molecular information and address task heterogeneity of different molecular properties, Meta-MGNN further incorporates molecular structure, attribute based self-supervised modules and self-attentive task weights into the former framework, strengthening the whole learning model. Extensive experiments on two public multi-property datasets demonstrate that Meta-MGNN outperforms a variety of state-of-the-art methods.