Timezone: »
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 counts.This paper proposes a new multi-level framework that jointly models node-level properties and graph-level statistics, as mutually reinforcing sources of information. We introduce a new micro-macro training objective for graph generation that combines node-level and graph-level losses. We utilize the micro-macro objective to improve graph generation with a GraphVAE, a well-established model based on graph-level latent variables, that provides fast training and generation time for medium-sized graphs. Our experiments show that adding micro-macro modeling to the GraphVAE model improves graph quality scores up to 2 orders of magnitude on five benchmark datasets, while maintaining the GraphVAE generation speed advantage.
Author Information
Kiarash Zahirnia (Simon Fraser University)
Oliver Schulte (Simon Fraser University)

Bio: Oliver Schulte is a Professor in the School of Computing Science at Simon Fraser University, Vancouver, Canada. He received his Ph.D. from Carnegie Mellon University in 1997. His current research focuses on machine learning for structured, relational, and event data. He has published sports analytics papers in leading AI and machine learning venues, and co-organized two hockey analytics conferences. The last two years he has worked with Sportlogiq, a leading hockey data provider. While he has won some nice awards, his biggest claim to fame may be a draw against chess world champion Gary Kasparov.
Parmis Naddaf (Simon Fraser University)
Ke Li (Simon Fraser University)
More from the Same Authors
-
2023 Poster: NeRF Revisited: Fixing Quadrature Instability in Volume Rendering »
Mikaela Angelina Uy · Guandao Yang · Kiyohiro Nakayama · Leonidas Guibas · Ke Li -
2023 Poster: Cause-Effect Inference in Location-Scale Noise Models: Maximum Likelihood vs. Independence Testing »
Xiangyu Sun · Oliver Schulte -
2023 Poster: Neural Graph Generation from Graph Statistics »
Kiarash Zahirnia · Oliver Schulte · Mark Coates · Yaochen Hu -
2023 Poster: PAPR: Proximity Attention Point Rendering »
Shichong Peng · Yanshu Zhang · Alireza Moazeni · Ke Li -
2022 Spotlight: CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis »
Shichong Peng · Seyed Alireza Moazenipourasil · Ke Li -
2022 Spotlight: Lightning Talks 5B-1 »
Devansh Arpit · Xiaojun Xu · Zifan Shi · Ivan Skorokhodov · Shayan Shekarforoush · Zhan Tong · Yiqun Wang · Shichong Peng · Linyi Li · Ivan Skorokhodov · Huan Wang · Yibing Song · David Lindell · Yinghao Xu · Seyed Alireza Moazenipourasil · Sergey Tulyakov · Peter Wonka · Yiqun Wang · Ke Li · David Fleet · Yujun Shen · Yingbo Zhou · Bo Li · Jue Wang · Peter Wonka · Marcus Brubaker · Caiming Xiong · Limin Wang · Deli Zhao · Qifeng Chen · Dit-Yan Yeung -
2022 Spotlight: Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders »
Kiarash Zahirnia · Oliver Schulte · Parmis Naddaf · Ke Li -
2022 Poster: Uncertainty-Aware Reinforcement Learning for Risk-Sensitive Player Evaluation in Sports Game »
Guiliang Liu · Yudong Luo · Oliver Schulte · Pascal Poupart -
2022 Poster: CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis »
Shichong Peng · Seyed Alireza Moazenipourasil · Ke Li -
2021 Poster: Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning »
Guiliang Liu · Xiangyu Sun · Oliver Schulte · Pascal Poupart -
2020 Poster: Learning Agent Representations for Ice Hockey »
Guiliang Liu · Oliver Schulte · Pascal Poupart · Mike Rudd · Mehrsan Javan