Unified theory of atom-centered representations and message-passing machine-learning schemes

Data-driven schemes that associate molecular and crystal structures with their microscopic properties share the need for a concise, effective description of the arrangement of their atomic constituents. Many types of models rely on descriptions of atom-centered environments, that are associated with an atomic property or with an atomic contribution to an extensive macroscopic quantity. Frameworks in this class can be understood in terms of atom-centered density correlations (ACDC), that are used as a basis for a body-ordered, symmetry-adapted expansion of the targets. Several other schemes, that gather information on the relationship between neighboring atoms using "message-passing" ideas, cannot be directly mapped to correlations centered around a single atom. We generalize the ACDC framework to include multi-centered information, generating representations that provide a complete linear basis to regress symmetric functions of atomic coordinates, and provides a coherent foundation to systematize our understanding of both atom-centered and message-passing, invariant and equivariant machine-learning schemes. This record contains the data and code required to reproduce the results from the corresponding paper, computing message-passing inspired machine learning features built on top of density correlation. The data used in this article is a subset of other existing datasets, which can be found online: - methane dataset: https://archive.materialscloud.org/record/2020.105 - NaCl dataset: https://github.com/dilkins/TENSOAP/tree/ea671154b3642b4ec879a4292a4dd4399ddbdea6/example/random_nacl - QM7 and QM9 with dipole moments: https://archive.materialscloud.org/record/2020.56