Completeness of Atomic Structure Representations (2302.14770v3)
Abstract: In this paper, we address the challenge of obtaining a comprehensive and symmetric representation of point particle groups, such as atoms in a molecule, which is crucial in physics and theoretical chemistry. The problem has become even more important with the widespread adoption of machine-learning techniques in science, as it underpins the capacity of models to accurately reproduce physical relationships while being consistent with fundamental symmetries and conservation laws. However, some of the descriptors that are commonly used to represent point clouds -- most notably those based on discretized correlations of the neighbor density, that underpin most of the existing ML models of matter at the atomic scale -- are unable to distinguish between special arrangements of particles in three dimensions. This makes it impossible to machine learn their properties. Atom-density correlations are provably complete in the limit in which they simultaneously describe the mutual relationship between all atoms, which is impractical. We present a novel approach to construct descriptors of \emph{finite} correlations based on the relative arrangement of particle triplets, which can be employed to create symmetry-adapted models with universal approximation capabilities, which have the resolution of the neighbor discretization as the sole convergence parameter. Our strategy is demonstrated on a class of atomic arrangements that are specifically built to defy a broad class of conventional symmetric descriptors, showcasing its potential for addressing their limitations.
- D. Widdowson and V. Kurlin, Recognizing rigid patterns of unlabeled point clouds by complete and continuous isometry invariants with no false negatives and no false positives, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023) pp. 1275–1284.
- S. N. Pozdnyakov and M. Ceriotti, Incompleteness of graph neural networks for points clouds in three dimensions, Mach. Learn.: Sci. Technol. 3, 045020 (2022).
- A. L. Patterson, Ambiguities in the X-Ray Analysis of Crystal Structures, Phys. Rev. 65, 195 (1944).
- M. Boutin and G. Kemper, On reconstructing n-point configurations from the distribution of distances or areas, Advances in Applied Mathematics 32, 709 (2004).
- A. Tasissa and R. Lai, Exact Reconstruction of Euclidean Distance Geometry Problem Using Low-Rank Matrix Completion, IEEE Trans. Inform. Theory 65, 3124 (2019).
- J. Behler and M. Parrinello, Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces, Phys. Rev. Lett. 98, 146401 (2007).
- M. J. Willatt, F. Musil, and M. Ceriotti, Atom-density representations for machine learning, J. Chem. Phys. 150, 154110 (2019).
- A. V. Shapeev, Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials, Multiscale Model. Simul. 14, 1153 (2016).
- B. Anderson, T. S. Hy, and R. Kondor, Cormorant: Covariant Molecular Neural Networks, in NeurIPS (2019) p. 10.
- R. Drautz, Atomic cluster expansion for accurate and transferable interatomic potentials, Phys. Rev. B 99, 014104 (2019).
- J. Behler, Atom-centered symmetry functions for constructing high-dimensional neural network potentials, The Journal of Chemical Physics 134, 074106 (2011).
- A. P. Bartók, R. Kondor, and G. Csányi, On representing chemical environments, Phys. Rev. B 87, 184115 (2013).
- A. Glielmo, C. Zeni, and A. De Vita, Efficient nonparametric n -body force fields from machine learning, Phys. Rev. B 97, 184307 (2018).
- R. Kakarala, The Bispectrum as a Source of Phase-Sensitive Invariants for Fourier Descriptors: A Group-Theoretic Approach, J Math Imaging Vis 44, 341 (2012).
- B. Parsaeifard and S. Goedecker, Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four-body interactions, J. Chem. Phys. 156, 034302 (2022).
- S. N. Pozdnyakov, M. J. Willatt, A. P. Bartók, C. Ortner, G. Csányi, and M. Ceriotti, Comment on “Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four-body interactions” [J. Chem. Phys. 156, 034302 (2022)], J. Chem. Phys. 157, 177101 (2022).
- J. Nigam, M. J. Willatt, and M. Ceriotti, Equivariant representations for molecular Hamiltonians and N -center atomic-scale properties, J. Chem. Phys. 156, 014115 (2022b).
- V. Kurlin, Exactly computable and continuous metrics on isometry classes of finite and 1-periodic sequences, arXiv preprint arXiv:2205.04388 (2022a).
- V. Kurlin, Computable complete invariants for finite clouds of unlabeled points under euclidean isometry, arXiv preprint arXiv:2207.08502 (2022b).
- S. N. Pozdnyakov and M. Ceriotti, Smooth, exact rotational symmetrization for deep learning on point clouds, in Advances in Neural Information Processing Systems (2023).
- T. Bereau, D. Andrienko, and O. A. Von Lilienfeld, Transferable Atomic Multipole Machine Learning Models for Small Organic Molecules, J. Chem. Theory Comput. 11, 3225 (2015).
- J. E. Moussa, Comment on “Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning”, Phys. Rev. Lett. 109, 059801 (2012).
- D. Widdowson and V. Kurlin, Resolving the data ambiguity for periodic crystals, Advances in Neural Information Processing Systems (Proceedings of NeurIPS 2022) 35 (2022).
- I. Boustani, Systematic ab initio investigation of bare boron clusters:mDetermination of the geometryand electronic structures of B n (n=2–14), Phys. Rev. B 55, 16426 (1997).
- J. Nigam, S. Pozdnyakov, and M. Ceriotti, Recursive evaluation and iterative contraction of N -body equivariant features, J. Chem. Phys. 153, 121101 (2020).
- J. Nigam and M. Ceriotti, Bispectrum degenerate B8 data, https://doi.org/10.5281/zenodo.8003294 (2023).
- F. Pietrucci and W. Andreoni, Graph Theory Meets Ab Initio Molecular Dynamics: Atomic Structures and Transformations at the Nanoscale, Phys. Rev. Lett. 107, 085504 (2011).
- K. Schütt, O. Unke, and M. Gastegger, Equivariant message passing for the prediction of tensorial properties and molecular spectra, in Int. Conf. Mach. Learn. (PMLR, 2021) pp. 9377–9388.