BenchML: an extensible pipelining framework for benchmarking representations of materials and molecules at scale
This work addresses the need for standardized benchmarking in materials and molecules research, offering a tool for method development and dataset assessment, though it is incremental as it builds on existing practices.
The authors tackled the problem of benchmarking diverse chemical representations by introducing BenchML, a framework that evaluates descriptor performance using simple regression and best ML practices, providing baselines and insights into representation merits and interrelatedness.
We introduce a machine-learning (ML) framework for high-throughput benchmarking of diverse representations of chemical systems against datasets of materials and molecules. The guiding principle underlying the benchmarking approach is to evaluate raw descriptor performance by limiting model complexity to simple regression schemes while enforcing best ML practices, allowing for unbiased hyperparameter optimization, and assessing learning progress through learning curves along series of synchronized train-test splits. The resulting models are intended as baselines that can inform future method development, next to indicating how easily a given dataset can be learnt. Through a comparative analysis of the training outcome across a diverse set of physicochemical, topological and geometric representations, we glean insight into the relative merits of these representations as well as their interrelatedness.