# Polyatomic Complexes: A topologically-informed learning representation for atomistic systems

arXiv: https://arxiv.org/abs/2409.15600 · HTML: https://mlsanity.com/paper/2409.15600/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 54 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 11 of 11)

- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Equivariant message passing for the prediction of tensorial properties and molecular spectra](https://mlsanity.com/paper/2102.03150/) (2021)
- [Pre-training Molecular Graph Representation with 3D Geometry](https://mlsanity.com/paper/2110.07728/) (2021)
- [Persistence Images: A Stable Vector Representation of Persistent Homology](https://mlsanity.com/paper/1507.06217/) (2015)
- [Scalars are universal: Equivariant machine learning, structured like classical physics](https://mlsanity.com/paper/2106.06610/) (2021)
- [SELFIES and the future of molecular string representations](https://mlsanity.com/paper/2204.00056/) (2022)
- [GAUCHE: A Library for Gaussian Processes in Chemistry](https://mlsanity.com/paper/2212.04450/) (2022)
- [Group SELFIES: A Robust Fragment-Based Molecular String Representation](https://mlsanity.com/paper/2211.13322/) (2022)
- [Data-Driven Discovery of Molecular Photoswitches with Multioutput Gaussian Processes](https://mlsanity.com/paper/2008.03226/) (2020)
- [Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning](https://mlsanity.com/paper/2003.12081/) (2020)
- [Topological Signal Processing over Generalized Cell Complexes](https://mlsanity.com/paper/2201.08993/) (2022)

## Built on by (most cited first, 1 of 1)

- [Topological Feature Compression for Molecular Graph Neural Networks](https://mlsanity.com/paper/2508.07807/) (2025)

## Abstract (arXiv)

A representation of a molecule or material should be invariant to the symmetries of physics, unique, continuous, efficient and general. These properties, however, are hard to satisfy at once: a descriptor invariant under the full orthogonal group O(3) gives a molecule and its mirror image the same value, and so cannot distinguish enantiomers whose properties differ. Pozdnyakov showed this follows from the invariance itself, not from a lack of parameters. We show the criteria can be met at once if the geometric map is graded by the sign character of O(3) and pooled multisymmetrically. We construct such a map Phi: its even block factors through the Gram matrix and is provably chirality-blind, while its parity-odd block of signed triple products separates enantiomers on an open dense full-measure set of interacting configurations. Two standard obstructions to uniqueness, fixed output length and componentwise pooling, are artifacts of the pooling rule, removed by multisymmetric power sums of order at most N. We establish uniqueness for a complete descriptor Phi^star built from the distance matrix, signed volumes and atom types, injective up to SE(3)× SN on all configurations. Phi^star is non-constructive, however; the implemented map is the bounded-cutoff Phi, generically injective, pooling at order 2, running in O(N2), or O(N) with neighbor lists. The algebraic core is machine-checked in Lean 4. Because the underlying object is a cell complex, it also yields invariant, stable topological features Psi (persistent homology and a Hodge-Laplacian spectrum) encoding global ring and cage structure invisible to bounded-cutoff descriptors. The pair (Phi,Psi) feeds a compact parity-graded equivariant transformer.