Graph convolutions that can finally model local structure
This work addresses a fundamental limitation in graph neural networks regarding local structure detection, which is particularly important for researchers and practitioners working with graph substructure analysis in domains like chemistry.
Modern graph neural networks struggle with detecting small cycles, which is crucial for tasks like chemistry. The authors propose a simple correction to the GIN convolution, enabling it to detect small cycles with minimal computational overhead. This model consistently improves performance on large multi-tasked molecular property datasets.
Despite quick progress in the last few years, recent studies have shown that modern graph neural networks can still fail at very simple tasks, like detecting small cycles. This hints at the fact that current networks fail to catch information about the local structure, which is problematic if the downstream task heavily relies on graph substructure analysis, as in the context of chemistry. We propose a very simple correction to the now standard GIN convolution that enables the network to detect small cycles with nearly no cost in terms of computation time and number of parameters. Tested on real life molecule property datasets, our model consistently improves performance on large multi-tasked datasets over all baselines, both globally and on a per-task setting.