Permutation Invariant Graph Generation via Score-Based Generative Modeling

2022년 04월 01일 (금) | 발표자: 윤태현

In this paper, authors show that graph generation via score-based generative modeling induces permutation invariance. Also they design a permutation equivariant, multi-channel graph neural network to model the gradient of the data distribution at the input graph (a.k.a., the score function).