Timezone: »

 
Poster
Graph Normalizing Flows
Jenny Liu · Aviral Kumar · Jimmy Ba · Jamie Kiros · Kevin Swersky

Wed Dec 11 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #142
in Deep Learning -- Generative Models »

We introduce graph normalizing flows: a new, reversible graph neural network model for prediction and generation. On supervised tasks, graph normalizing flows perform similarly to message passing neural networks, but at a significantly reduced memory footprint, allowing them to scale to larger graphs. In the unsupervised case, we combine graph normalizing flows with a novel graph auto-encoder to create a generative model of graph structures. Our model is permutation-invariant, generating entire graphs with a single feed-forward pass, and achieves competitive results with the state-of-the art auto-regressive models, while being better suited to parallel computing architectures.

Keywords: Generative Models · Relational Learning · Deep Learning · Algorithms -> Density Estimation; Algorithms
[ Paper]  [ Slides] 

Author Information

Jenny Liu (Vector Institute, University of Toronto)
Aviral Kumar (UC Berkeley)
Jimmy Ba (University of Toronto / Vector Institute)
Jamie Kiros (Google Inc.)
Kevin Swersky (Google)

More from the Same Authors