Kiarash Zahirnia — accepted AI-conference papers

2023

Neural Graph Generation from Graph Statistics

Kiarash Zahirnia, Yaochen Hu, Mark Coates, Oliver Schulte

NeurIPS 2023poster

We describe a new setting for learning a deep graph generative model (GGM) from aggregate graph statistics, rather than from the graph adjacency matrix. Matching the statistics of observed training graphs is the main approach for learning traditional GGMs (e.g, BTER, Chung-Lu, and Erdos-Renyi model…

Cited by 4 Source ↗PDF ↗Scholar ↗

2022

Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders

Kiarash Zahirnia, Oliver Schulte, Parmis Naddaf, Ke Li

NeurIPS 2022accept

Generative models for graph data are an important research topic in machine learning. Graph data comprise two levels that are typically analyzed separately: node-level properties such as the existence of a link between a pair of nodes, and global aggregate graph-level statistics, such as motif count…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗