Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions
arXiv:2106.01098
Abstract
Graph generative models are a highly active branch of machine learning. Given the steady development of new models of ever-increasing complexity, it is necessary to provide a principled way to evaluate and compare them. In this paper, we enumerate the desirable criteria for such a comparison metric and provide an overview of the status quo of graph generative model comparison in use today, which predominantly relies on the maximum mean discrepancy (MMD). We perform a systematic evaluation of MMD in the context of graph generative model comparison, highlighting some of the challenges and pitfalls researchers inadvertently may encounter. After conducting a thorough analysis of the behaviour of MMD on synthetically-generated perturbed graphs as well as on recently-proposed graph generative models, we are able to provide a suitable procedure to mitigate these challenges and pitfalls. We aggregate our findings into a list of practical recommendations for researchers to use when evaluating graph generative models.
arXiv commentAccepted as a Spotlight presentation at ICLR 2022
References in corpus (11)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Statistical topological data analysis using persistence landscapes
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
- Efficient Graph Generation with Graph Recurrent Attention Networks
- Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
- NetLSD: Hearing the Shape of a Graph
- Persistence paths and signature features in topological data analysis
- A Test of Relative Similarity For Model Selection in Generative Models
- The Shape of Data: Intrinsic Distance for Data Distributions
- Topological Graph Neural Networks