There are three key properties of scene graph that have been underexplored in recent works: namely, the edge direction information, the difference in priority between nodes, and the long-tailed distribution of relationships.
In particular, we 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).
Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e. g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach".
Indeed, as we demonstrate, their performance degrades significantly for larger molecules.
Minimum DFS codes are canonical labels and capture the graph structure precisely along with the label information.
Our model generates graphs one block of nodes and associated edges at a time.
Additionally, combining GCN modules with different propagation rules is critical to the representation power of GCNs.
We show for a wide variety of molecules we can quickly compute the correct molecular structure, and can detect with reasonable certainty when our method cannot.
For this, we introduce the Toulouse Road Network dataset, based on real-world publicly-available data.