A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels

Sep 28, 2020 (edited Jan 25, 2021)ICLR 2021 PosterReaders: Everyone
• Keywords: Group Equivariant Convolution, Steerable Kernel, Quantum Mechanics, Wigner-Eckart Theorem, Representation Theory, Harmonic Analysis, Peter-Weyl Theorem
• Abstract: Group equivariant convolutional networks (GCNNs) endow classical convolutional networks with additional symmetry priors, which can lead to a considerably improved performance. Recent advances in the theoretical description of GCNNs revealed that such models can generally be understood as performing convolutions with \$G\$-steerable kernels, that is, kernels that satisfy an equivariance constraint themselves. While the \$G\$-steerability constraint has been derived, it has to date only been solved for specific use cases - a general characterization of \$G\$-steerable kernel spaces is still missing. This work provides such a characterization for the practically relevant case of \$G\$ being any compact group. Our investigation is motivated by a striking analogy between the constraints underlying steerable kernels on the one hand and spherical tensor operators from quantum mechanics on the other hand. By generalizing the famous Wigner-Eckart theorem for spherical tensor operators, we prove that steerable kernel spaces are fully understood and parameterized in terms of 1) generalized reduced matrix elements, 2) Clebsch-Gordan coefficients, and 3) harmonic basis functions on homogeneous spaces.
• One-sentence Summary: We parameterize equivariant convolution kernels by proving a generalization of the Wigner-Eckart theorem for spherical tensor operators.
• Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
12 Replies