Multitask Learning On Graph Neural Networks Applied To Molecular Property Predictions

10/29/2019
by   Fabio Capela, et al.
39

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 methods. 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 have been observed. Most importantly, datasets with a small amount of data points reach better results without the need of augmentation. The improvement is an effect of data augmentation.

READ FULL TEXT

page 4

page 8

research
11/23/2020

Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction

Graph neural networks have recently become a standard method for analysi...
research
11/24/2020

Lipophilicity Prediction with Multitask Learning and Molecular Substructures Representation

Lipophilicity is one of the factors determining the permeability of the ...
research
11/25/2022

Extreme Acceleration of Graph Neural Network-based Prediction Models for Quantum Chemistry

Molecular property calculations are the bedrock of chemical physics. Hig...
research
10/07/2022

ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction

In this work, we propose the novel Prototypical Graph Regression Self-ex...
research
04/02/2019

Are Learned Molecular Representations Ready For Prime Time?

Advancements in neural machinery have led to a wide range of algorithmic...
research
03/22/2022

Bioplastic Design using Multitask Deep Neural Networks

Non-degradable plastic waste stays for decades on land and in water, jeo...

Please sign up or login with your details

Forgot password? Click here to reset