Papers › Graphite: Iterative Generative Modeling of Graphs
Graphite: Iterative Generative Modeling of Graphs
Aditya Grover, Aaron Zweig, Stefano Ermon
Graphs are a fundamental abstraction for modeling relational data. However, graphs are discrete and combinatorial in nature, and learning representations suitable for machine learning tasks poses statistical and computational challenges. In this work, we propose Graphite, an algorithmic framework for unsupervised learning of representations over nodes in large graphs using deep latent variable generative models. Our model parameterizes variational autoencoders (VAE) with graph neural networks, and uses a novel iterative graph refinement strategy inspired by low-rank approximations for decoding. On a wide variety of synthetic and benchmark datasets, Graphite outperforms competing approaches for the tasks of density estimation, link prediction, and node classification. Finally, we derive a theoretical connection between message passing in graph neural networks and mean-field variational inference.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Link Prediction | Citeseer | sGraphite-VAE | AP | 95.4% | #8 of 13 | Archive leaderboard | report |
| Link Prediction | Citeseer | sGraphite-VAE | AUC | 94.1% | #8 of 13 | Archive leaderboard | report |
| Node Classification | Citeseer | Graphite | Accuracy | 71.0 ± 0.07 | #57 of 71 | Archive leaderboard | report |
| Node Classification | Cora | Graphite | Accuracy | 82.1% ± 0.06% | #57 of 73 | Archive leaderboard | report |
| Node Classification | Pubmed | Graphite | Accuracy | 79.3 ± 0.03 | #48 of 70 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections