Integrating Transformer and Autoencoder Techniques with Spectral Graph Algorithms for the Prediction of Scarcely Labeled Molecular Data

TL;DR

This paper introduces innovative graph-based models combining transformer, autoencoder, and spectral graph algorithms to improve property prediction in molecular data with scarce labels, demonstrating high accuracy with minimal labeled data.

Contribution

It presents novel integration of MBO techniques with transformer and autoencoder models for scarcely-labeled molecular data prediction, validated on multiple benchmarks.

Findings

Models perform well with as little as 1% labeled data.

Proposed methods outperform traditional classifiers like SVM and random forests.

Extensive experiments confirm the effectiveness of the integrated approach.

Abstract

In molecular and biological sciences, experiments are expensive, time-consuming, and often subject to ethical constraints. Consequently, one often faces the challenging task of predicting desirable properties from small data sets or scarcely-labeled data sets. Although transfer learning can be advantageous, it requires the existence of a related large data set. This work introduces three graph-based models incorporating Merriman-Bence-Osher (MBO) techniques to tackle this challenge. Specifically, graph-based modifications of the MBO scheme are integrated with state-of-the-art techniques, including a home-made transformer and an autoencoder, in order to deal with scarcely-labeled data sets. In addition, a consensus technique is detailed. The proposed models are validated using five benchmark data sets. We also provide a thorough comparison to other competing methods, such as support vector machines, random forests, and gradient boosting decision trees, which are known for their good performance on small data sets. The performances of various methods are analyzed using residue-similarity (R-S) scores and R-S indices. Extensive computational experiments and theoretical analysis show that the new models perform very well even when as little as 1% of the data set is used as labeled data.