AgraSSt: Approximate Graph Stein Statistics for Interpretable Assessment of Implicit Graph Generators

Wenkai Xu · Gesine D Reinert

Hall J #228

Keywords: [ kernel method ] [ synthetic graph generator ] [ Stein's method ]

[ Abstract ]
[ Paper [ Poster [ OpenReview
Tue 29 Nov 9 a.m. PST — 11 a.m. PST


We propose and analyse a novel statistical procedure, coined AgraSSt, to assess the quality of graph generators which may not be available in explicit forms. In particular, AgraSSt can be used to determine whether a learned graph generating process is capable of generating graphs which resemble a given input graph. Inspired by Stein operators for random graphs, the key idea of AgraSSt is the construction of a kernel discrepancy based on an operator obtained from the graph generator. AgraSSt can provide interpretable criticisms for a graph generator training procedure and help identify reliable sample batches for downstream tasks. We give theoretical guarantees for a broad class of random graph models. Moreover, we provide empirical results on both synthetic input graphs with known graph generation procedures, and real-world input graphs that the state-of-the-art (deep) generative models for graphs are trained on.

Chat is not available.