Why Deep Models Often cannot Beat Non-deep Counterparts on Molecular Property Prediction?
This work addresses the problem of inefficient deep learning for drug discovery researchers, revealing that deep models often fail to beat simpler methods, which is incremental as it builds on prior observations.
The study benchmarks 12 models on 14 molecular datasets, finding that deep models generally cannot outperform non-deep ones in molecular property prediction, with tree models using molecular fingerprints performing best.
Molecular property prediction (MPP) is a crucial task in the drug discovery pipeline, which has recently gained considerable attention thanks to advances in deep neural networks. However, recent research has revealed that deep models struggle to beat traditional non-deep ones on MPP. In this study, we benchmark 12 representative models (3 non-deep models and 9 deep models) on 14 molecule datasets. Through the most comprehensive study to date, we make the following key observations: \textbf{(\romannumeral 1)} Deep models are generally unable to outperform non-deep ones; \textbf{(\romannumeral 2)} The failure of deep models on MPP cannot be solely attributed to the small size of molecular datasets. What matters is the irregular molecule data pattern; \textbf{(\romannumeral 3)} In particular, tree models using molecular fingerprints as inputs tend to perform better than other competitors. Furthermore, we conduct extensive empirical investigations into the unique patterns of molecule data and inductive biases of various models underlying these phenomena.