Multitask Learning On Graph Neural Networks Applied To Molecular Property Predictions
This work addresses molecular property prediction in chemistry, offering incremental improvements through multitask learning.
The paper tackled the challenge of predicting molecular properties by introducing a multitask learning approach using graph neural networks, achieving new state-of-the-art results with reduced model variance and improved performance on small datasets without augmentation.
Prediction of molecular properties, including physico-chemical properties, is a challenging task in chemistry. Herein we present a new state-of-the-art multitask prediction method based on existing graph neural network models. We have used different architectures for our models and the results clearly demonstrate that multitask learning can improve model performance. Additionally, a significant reduction of variance in the models has been observed. Most importantly, datasets with a small amount of data points reach better results without the need of augmentation.