Litcius/Paper detail

Molecular property prediction in the ultra‐low data regime

Basem A. Eraqi, Dmitrii Khizbullin, Shashank S. Nagaraja, S. Mani Sarathy

2025Communications Chemistry9 citationsDOIOpen Access PDF

Abstract

Data scarcity remains a major obstacle to effective machine learning in molecular property prediction and design, affecting diverse domains such as pharmaceuticals, solvents, polymers, and energy carriers. Although multi-task learning (MTL) can leverage correlations among properties to improve predictive performance, imbalanced training datasets often degrade its efficacy through negative transfer. Here, we present adaptive checkpointing with specialization (ACS), a training scheme for multi-task graph neural networks that mitigates detrimental inter-task interference while preserving the benefits of MTL. We validate ACS on multiple molecular property benchmarks, where it consistently surpasses or matches the performance of recent supervised methods. To illustrate its practical utility, we deploy ACS in a real-world scenario of predicting sustainable aviation fuel properties, showing that it can learn accurate models with as few as 29 labeled samples. By enabling reliable property prediction in low-data regimes, ACS broadens the scope and accelerates the pace of artificial intelligence-driven materials discovery and design. Multi-task learning has been shown to improve the predicting performance of machine learning models despite data scarcity, but imbalanced training datasets often degrade its efficacy through negative transfer. Here, the authors introduce adaptive checkpointing with specialization, a training scheme that mitigates detrimental inter-task interference, and demonstrate its practical utility by predicting sustainable aviation fuel properties.

Topics & Concepts

Property (philosophy)Environmental scienceMaterials scienceComputer sciencePhilosophyEpistemologyMachine Learning in Materials ScienceMetabolomics and Mass Spectrometry StudiesComputational Drug Discovery Methods
Molecular property prediction in the ultra‐low data regime | Litcius