Contributed Talk 5
Workshop: Differential Geometry meets Deep Learning (DiffGeo4DL)

Contributed Talk 5: A New Neural Network Architecture Invariant to the Action of Symmetry Subgroups

Mete Ozay · Piotr Kicki · Piotr Skrzypczynski

Abstract: We propose a computationally efficient $G$-invariant neural network that approximates functions invariant to the action of a given permutation subgroup $G \leq S_n$ of the symmetric group on input data. The key element of the proposed network architecture is a new $G$-invariant transformation module, which produces a $G$-invariant latent representation of the input data. Theoretical considerations are supported by numerical experiments, which demonstrate the effectiveness and strong generalization properties of the proposed method in comparison to other $G$-invariant neural networks.

Chat is not available.