On the Power of Edge Independent Graph Models
arXiv:2111.00048
Abstract
Why do many modern neural-network-based graph generative models fail to reproduce typical real-world network characteristics, such as high triangle density? In this work we study the limitations of edge independent random graph models, in which each edge is added to the graph independently with some probability. Such models include both the classic Erdös-Rényi and stochastic block models, as well as modern generative models such as NetGAN, variational graph autoencoders, and CELL. We prove that subject to a bounded overlap condition, which ensures that the model does not simply memorize a single graph, edge independent models are inherently limited in their ability to generate graphs with high triangle and other subgraph densities. Notably, such high densities are known to appear in real-world social networks and other graphs. We complement our negative results with a simple generative model that balances overlap and accuracy, performing comparably to more complex models in reconstructing many graph statistics.
References in corpus (10)
- Emergence of scaling in random networks
- Powerlaw: a Python package for analysis of heavy-tailed distributions
- Variational Graph Auto-Encoders
- Kronecker Graphs: An Approach to Modeling Networks
- Random Geometric Graphs
- MolGAN: An implicit generative model for small molecular graphs
- Learning Deep Generative Models of Graphs
- Efficient Graph Generation with Graph Recurrent Attention Networks
- The impossibility of low rank representations for triangle-rich complex networks
- Degree Relations of Triangles in Real-world Networks and Models