ON THE SCALABILITY OF GNNS FOR MOLECULAR GRAPHS

Maciej Sypetkowski, Frederik Wenkel, Farimah Poursafaei, Nia Dickson, Karush Suri, Philip Fradkin, Dominique Beaini

Keywords: Graph Neural Networks, Scaling Laws, Molecular Biology

TL;DR: We study scaling laws of Graph Neural Networks on 2D molecular graphs during pretraining as well as finetuning.

Abstract:

Scaling deep learning models has been at the heart of recent revolutions in language modelling and image generation. Practitioners have observed a strong relationship between model size, dataset size, and performance. However, structure-based architectures such as Graph Neural Networks (GNNs) are yet to show the benefits of scale mainly due to the lower efficiency of sparse operations, large data requirements, and lack of clarity about the effectiveness of various architectures.
We address this drawback by studying their scaling behavior. Specifically, we analyze message-passing networks, graph Transformers, and hybrid architectures on the largest public collection of 2D molecular graphs.
For the first time, we observe that GNNs benefit tremendously from the increasing scale of depth, width, number of molecules, number of labels, and the diversity in the pretraining datasets, resulting in a 30.25\% improvement when scaling to 1 billion parameters and 28.98\% improvement when increasing size of dataset to eightfold.
We further demonstrate strong finetuning scaling behavior on 38 tasks, outclassing previous large models. We hope that our work paves the way for an era where foundational GNNs drive pharmaceutical drug discovery.

Submission Number: 22