# Auto-decoding Graphs

arXiv: https://arxiv.org/abs/2006.02879 · HTML: https://mlsanity.com/paper/2006.02879/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2020.

## Built on by (most cited first, 2 of 2)

- [SANGEA: Scalable and Attributed Network Generation](https://mlsanity.com/paper/2309.15648/) (2023)
- [Gransformer: Transformer-based Graph Generation](https://mlsanity.com/paper/2203.13655/) (2022)

## Abstract (arXiv)

We present an approach to synthesizing new graph structures from empirically specified distributions. The generative model is an auto-decoder that learns to synthesize graphs from latent codes. The graph synthesis model is learned jointly with an empirical distribution over the latent codes. Graphs are synthesized using self-attention modules that are trained to identify likely connectivity patterns. Graph-based normalizing flows are used to sample latent codes from the distribution learned by the auto-decoder. The resulting model combines accuracy and scalability. On benchmark datasets of large graphs, the presented model outperforms the state of the art by a factor of 1.5 in mean accuracy and average rank across at least three different graph statistics, with a 2x speedup during inference.