Sparse hierarchical representation learning on molecular graphs
This work addresses a gap in graph-based machine learning for drug discovery by enabling hierarchical pooling with edge features, though it is incremental as it builds on existing architectures.
The authors tackled the problem of sparse hierarchical representation learning on molecular graphs with edge features, which previous methods assumed absent, and achieved state-of-the-art results on three out of four MoleculeNet benchmarks while improving training speed.
Architectures for sparse hierarchical representation learning have recently been proposed for graph-structured data, but so far assume the absence of edge features in the graph. We close this gap and propose a method to pool graphs with edge features, inspired by the hierarchical nature of chemistry. In particular, we introduce two types of pooling layers compatible with an edge-feature graph-convolutional architecture and investigate their performance for molecules relevant to drug discovery on a set of two classification and two regression benchmark datasets of MoleculeNet. We find that our models significantly outperform previous benchmarks on three of the datasets and reach state-of-the-art results on the fourth benchmark, with pooling improving performance for three out of four tasks, keeping performance stable on the fourth task, and generally speeding up the training process.