A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks

9 October 2019

Papers citing "A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks"

10 / 10 papers shown

Title
Equivariant Polynomials for Graph Neural Networks Omri Puny Derek Lim B. Kiani Haggai Maron Y. Lipman 24 31 0 22 Feb 2023
SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks Christopher Morris Gaurav Rattan Sandra Kiefer Siamak Ravanbakhsh 42 39 0 25 Mar 2022
Sign and Basis Invariant Networks for Spectral Graph Representation Learning Derek Lim Joshua Robinson Lingxiao Zhao Tess E. Smidt S. Sra Haggai Maron Stefanie Jegelka 43 139 0 25 Feb 2022
Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters Takanori Maehara Hoang NT 35 2 0 05 Nov 2021
SE(3) Equivariant Graph Neural Networks with Complete Local Frames Weitao Du He Zhang Yuanqi Du Qi Meng Wei-Neng Chen Bin Shao Tie-Yan Liu 48 79 0 26 Oct 2021
Reconstruction for Powerful Graph Representations Leonardo Cotta Christopher Morris Bruno Ribeiro AI4CE 127 78 0 01 Oct 2021
On the Universality of Rotation Equivariant Point Cloud Networks Nadav Dym Haggai Maron 3DPC 27 78 0 06 Oct 2020
Expressive Power of Invariant and Equivariant Graph Neural Networks Waïss Azizian Marc Lelarge 20 111 0 28 Jun 2020
word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Data Martin Grohe 27 170 0 27 Mar 2020
On Learning Sets of Symmetric Elements Haggai Maron Or Litany Gal Chechik Ethan Fetaya 22 132 0 20 Feb 2020