Attention and Edge Memory Convolution for Bioactivity Prediction

摘要

We present some augmentations to literature Message Passing Neural Network (MPNN) architectures and benchmark their performances against a wide range of chemically and pharmaceutically relevant datasets. We analyse the effects of activation function for regularisation, we propose a new graph attention mechanism, and we implement a new edge-based memory system that should maximise the effectiveness of hidden state usage by directing and isolating information flow around the graph. We compare our results to the MolNet [14] benchmarking paper results on graph-based techniques, and also investigate the effect of method performance as a function of dataset preprocessing.