Topological Feature Compression for Molecular Graph Neural Networks

TL;DR

This paper introduces a novel GNN architecture that efficiently combines topological signals with molecular features, improving accuracy and interpretability in molecular property prediction tasks.

Contribution

The work presents a new GNN model that integrates compressed topological information with molecular features, enhancing performance and interpretability while maintaining computational efficiency.

Findings

Achieved state-of-the-art results across multiple benchmarks.

Demonstrated superior robustness and accuracy.

Provided an interpretable and parameter-efficient model.

Abstract

Recent advances in molecular representation learning have produced highly effective encodings of molecules for numerous cheminformatics and bioinformatics tasks. However, extracting general chemical insight while balancing predictive accuracy, interpretability, and computational efficiency remains a major challenge. In this work, we introduce a novel Graph Neural Network (GNN) architecture that combines compressed higher-order topological signals with standard molecular features. Our approach captures global geometric information while preserving computational tractability and human-interpretable structure. We evaluate our model across a range of benchmarks, from small-molecule datasets to complex material datasets, and demonstrate superior performance using a parameter-efficient architecture. We achieve the best performing results in both accuracy and robustness across almost all benchmarks. We open source all code \footnote{All code and results can be found on Github https://github.com/rahulkhorana/TFC-PACT-Net}.