paper-with-me

홈 › Papers

Graph Automorphism Group Equivariant Neural Networks

2023-07-15 · Edward Pearce-Crump, William J. Knottenbelt

Permutation equivariant neural networks are typically used to learn from data that lives on a graph. However, for any graph $G$ that has $n$ vertices, using the symmetric group $S_n$ as its group of symmetries does not take into account the relations that exist between the vertices. Given that the actual group of symmetries is the automorphism group Aut$(G)$, we show how to construct neural networks that are equivariant to Aut$(G)$ by obtaining a full characterisation of the learnable, linear, Aut$(G)$-equivariant functions between layers that are some tensor power of $\mathbb{R}^{n}$. In particular, we find a spanning set of matrices for these layer functions in the standard basis of $\mathbb{R}^{n}$. This result has important consequences for learning from data whose group of symmetries is a finite group because a theorem by Frucht (1938) showed that any finite group is isomorphic to the automorphism group of a graph.

📄 PDF Abstract BibTeX arXiv:2307.07810

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Any-Subgroup Equivariant Networks via Symmetry Breaking

2026-03-19 · Abhinav Goel, Derek Lim, Hannah Lawrence, Stefanie Jegelka 외 arxiv

The inclusion of symmetries as an inductive bias, known as equivariance, often improves generalization on geometric data (e.g. grids, sets, and graphs). However, equivariant architectures are usually highly constrained, …

Transfer Learning

Autobahn: Automorphism-based Graph Neural Nets

2021-03-02 · NeurIPS 2021 12 · Erik Henning Thiede, Wenda Zhou, Risi Kondor

We introduce Automorphism-based graph neural networks (Autobahn), a new family of graph neural networks. In an Autobahn, we decompose the graph into a collection of subgraphs and apply local convolutions that are equivar…

Graph Neural Network

Approximately Equivariant Graph Networks

2023-08-21 · NeurIPS 2023 11 · Ningyuan Huang, Ron Levie, Soledad Villar

Graph neural networks (GNNs) are commonly described as being permutation equivariant with respect to node relabeling in the graph. This symmetry of GNNs is often compared to the translation equivariance of Euclidean conv…

Image InpaintingPose EstimationTranslation

Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks

2026-07-28 · Xin Xu, Siru Tao, Kaizhen Tan arxiv

A gradient-based GNN explainer given a molecule with two chemically equivalent nitro groups assigns them attribution scores that are equal to the last bit. It cannot do otherwise: message passing is exactly permutation e…

Subgraph Permutation Equivariant Networks

2021-11-23 · Joshua Mitton, Roderick Murray-Smith

In this work we develop a new method, named Sub-graph Permutation Equivariant Networks (SPEN), which provides a framework for building graph neural networks that operate on sub-graphs, while using a base update function …

GPU