search

lrjconan / GRAN

Efficient Graph Generation with Graph Recurrent Attention Networks, Deep Generative Model of Graphs, Graph Neural Networks, NeurIPS 2019
MIT License
469 stars 96 forks source link

Loss fix #11

Closed adamoyoung closed 4 years ago

adamoyoung commented 4 years ago

Corrected loss function to make it consistent with the paper: it is now computing the log sum of probabilities for each of the node orderings instead of the log product.