Learning the Graphical Nature of Symmetries
Rashid Barket, Enrico Grimaldi, Yacoub Hendi, Edward Hirst, Adam Onus, Harmeet Singh
stat.ML, cs.LG, math.CO, math.GR
Submitted: 2026-07-13
Comments: 32 pages; 18 figures
Code: https://github.com/Engrima18/CayleyNet
License: http://creativecommons.org/licenses/by/4.0/
The gist: Finite groups are rigid algebraic objects, whose Cayley graphs expose a rich network geometry through which group-theoretic structure can be measured, compared, and learned.
Terminology
Abstract
Finite groups are rigid algebraic objects, whose Cayley graphs expose a rich network geometry through which group-theoretic structure can be measured, compared, and learned. In this paper, a dataset of 131, 406 Cayley graphs is constructed, covering all groups of order at most 767 except order 512, recording exact algebraic labels for group properties together with a broad collection of graph, cycle, distance, and spectral statistics. This census aims to provide novel benchmarks for studying how finite-group properties are reflected in Cayley graph observables. It also yields new enumerative contributions: alongside recovering known OEIS sequences for standard group classes, new sequences for monolithic groups and for groups generated by at most three, four, and five elements are contributed to the OEIS. The accompanying network analysis identifies several empirical regularities and formulates testable conjectures, including relationships involving square clustering, Cayley graph diameter, average graph disorder, and spectral eigengaps of nilpotent groups. Finally, a comparison between classical models, an MLP, and graph neural network architectures is performed for predicting algebraic group properties directly from Cayley graph data. The results show that engineered graph statistics are highly informative, while GNNs, especially GIN and in some fixed-order settings GCN, can recover substantial structural signal directly from the graph. Such that graph-aware architectures show phases of optimality on these group-theoretic graph representations.
Sources
- How Powerful are Graph Neural Networks?
- Learning to be Simple
- Diffusion Models for Cayley Graphs
- CayleyPy RL: Pathfinding and Reinforcement Learning on Cayley Graphs
- CayleyPy Growth: Efficient growth computations and hundreds of new conjectures on Cayley graphs (Brief version)
- CayleyPy-4: AI-Holography. Towards analogs of holographic string dualities for AI tasks
- Cayley Graph Propagation
- Learning 3-Manifold Triangulations
- Cluster Algebras: Network Science and Machine Learning
- The Laplacian spectral ratio of connected graphs
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches