BenchML: An extensible pipelining framework for benchmarking representations of materials and molecules at scale
Poelking C, Faber FA, Cheng B. 2022. BenchML: An extensible pipelining framework for benchmarking representations of materials and molecules at scale. Machine Learning: Science and Technology. 3(4), 040501.
Download
Journal Article
| Published
| English
Scopus indexed
Author
Poelking, Carl;
Faber, Felix A;
Cheng, BingqingISTA
Department
Abstract
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, in addition 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.
Publishing Year
Date Published
2022-11-17
Journal Title
Machine Learning: Science and Technology
Publisher
IOP Publishing
Acknowledgement
C P acknowledges funding from Astex through the Sustaining Innovation Program under the Milner Consortium. B C acknowledges resources provided by the Cambridge Tier-2 system operated by the University of Cambridge Research Computing Service funded by EPSRC Tier-2 capital Grant EP/P020259/1. F A F acknowledges funding from the Swiss National Science Foundation (Grant No. P2BSP2_191736).
Volume
3
Issue
4
Article Number
040501
ISSN
IST-REx-ID
Cite this
Poelking C, Faber FA, Cheng B. BenchML: An extensible pipelining framework for benchmarking representations of materials and molecules at scale. Machine Learning: Science and Technology. 2022;3(4). doi:10.1088/2632-2153/ac4d11
Poelking, C., Faber, F. A., & Cheng, B. (2022). BenchML: An extensible pipelining framework for benchmarking representations of materials and molecules at scale. Machine Learning: Science and Technology. IOP Publishing. https://doi.org/10.1088/2632-2153/ac4d11
Poelking, Carl, Felix A Faber, and Bingqing Cheng. “BenchML: An Extensible Pipelining Framework for Benchmarking Representations of Materials and Molecules at Scale.” Machine Learning: Science and Technology. IOP Publishing, 2022. https://doi.org/10.1088/2632-2153/ac4d11.
C. Poelking, F. A. Faber, and B. Cheng, “BenchML: An extensible pipelining framework for benchmarking representations of materials and molecules at scale,” Machine Learning: Science and Technology, vol. 3, no. 4. IOP Publishing, 2022.
Poelking C, Faber FA, Cheng B. 2022. BenchML: An extensible pipelining framework for benchmarking representations of materials and molecules at scale. Machine Learning: Science and Technology. 3(4), 040501.
Poelking, Carl, et al. “BenchML: An Extensible Pipelining Framework for Benchmarking Representations of Materials and Molecules at Scale.” Machine Learning: Science and Technology, vol. 3, no. 4, 040501, IOP Publishing, 2022, doi:10.1088/2632-2153/ac4d11.
All files available under the following license(s):
Creative Commons Attribution 4.0 International Public License (CC-BY 4.0):
Main File(s)
File Name
2022_MachLearning_Poelking.pdf
13.81 MB
Access Level
Open Access
Date Uploaded
2023-01-23
MD5 Checksum
8930d4ad6ed9b47358c6f1a68666adb6
Export
Marked PublicationsOpen Data ISTA Research Explorer