GraphBPE: Molecular Graphs Meet Byte-Pair Encoding
This work addresses a data preprocessing gap in molecular machine learning, offering an incremental improvement for researchers and practitioners in chemistry and drug discovery.
The paper tackles the problem of data preprocessing for molecular graphs by proposing GraphBPE, a method that tokenizes molecular graphs into substructures inspired by Byte-Pair Encoding, and shows it boosts model performance on small classification datasets and performs competitively on various tasks.
With the increasing attention to molecular machine learning, various innovations have been made in designing better models or proposing more comprehensive benchmarks. However, less is studied on the data preprocessing schedule for molecular graphs, where a different view of the molecular graph could potentially boost the model's performance. Inspired by the Byte-Pair Encoding (BPE) algorithm, a subword tokenization method popularly adopted in Natural Language Processing, we propose GraphBPE, which tokenizes a molecular graph into different substructures and acts as a preprocessing schedule independent of the model architectures. Our experiments on 3 graph-level classification and 3 graph-level regression datasets show that data preprocessing could boost the performance of models for molecular graphs, and GraphBPE is effective for small classification datasets and it performs on par with other tokenization methods across different model architectures.