Papers › Scalable Deep Generative Modeling for Sparse Graphs

Scalable Deep Generative Modeling for Sparse Graphs

28 Jun 2020ICML 2020 1arXiv:2006.15502archive 2025-07-28

Hanjun Dai, Azade Nazi, Yujia Li, Bo Dai, Dale Schuurmans

Learning graph generative models is a challenging task for deep learning and has wide applicability to a range of domains like chemistry, biology and social science. However current deep neural methods suffer from limited scalability: for a graph with n nodes and m edges, existing deep neural methods require Ω(n²) complexity by building up the adjacency matrix. On the other hand, many real world graphs are actually sparse in the sense that m≪n². Based on this, we develop a novel autoregressive model, named BiGG, that utilizes this sparsity to avoid generating the full adjacency matrix, and importantly reduces the graph generation time complexity to O((n + m)logn). Furthermore, during training this autoregressive model can be parallelized with O(logn) synchronization stages, which makes it much more efficient than other autoregressive models that require Ω(n). Experiments on several benchmarks show that the proposed approach not only scales to orders of magnitude larger graphs than previously possible with deep autoregressive graph generative models, but also yields better graph generation quality.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

google-research/google-research officialmentioned in papertf report

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

Graph Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: BiGG

BiGG

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