Compressing physical properties of atomic species for improving predictive chemistry
This work addresses the challenge of efficiently exploring chemical space for predictive chemistry, offering a domain-specific improvement that is incremental in nature.
The authors tackled the problem of representing atomic species in machine learning for chemistry by introducing a compressed representation called elemental modes, which captures periodic table nuances and atomic similarities, and demonstrated its effectiveness in improving various predictive tasks beyond just accuracy gains.
The answers to many unsolved problems lie in the intractable chemical space of molecules and materials. Machine learning techniques are rapidly growing in popularity as a way to compress and explore chemical space efficiently. One of the most important aspects of machine learning techniques is representation through the feature vector, which should contain the most important descriptors necessary to make accurate predictions, not least of which is the atomic species in the molecule or material. In this work we introduce a compressed representation of physical properties for atomic species we call the elemental modes. The elemental modes provide an excellent representation by capturing many of the nuances of the periodic table and the similarity of atomic species. We apply the elemental modes to several different tasks for machine learning algorithms and show that they enable us to make improvements to these tasks even beyond simply achieving higher accuracy predictions.