Abstract | ||
---|---|---|
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. |
Year | Venue | DocType |
---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | Conference |
Volume | ISSN | Citations |
32 | 1049-5258 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liu, Jenny | 1 | 0 | 0.34 |
Aviral Kumar | 2 | 3 | 8.47 |
Lei Jimmy Ba | 3 | 8887 | 296.55 |
Kiros, Ryan | 4 | 2265 | 94.80 |
Kevin Swersky | 5 | 1118 | 52.13 |