TD-GEN: Graph Generation With Tree Decomposition

TL;DR

TD-GEN introduces a novel graph generation framework leveraging tree decomposition, reducing decision complexity and improving performance, with a permutation invariant model that incrementally generates graphs respecting tree structures.

Contribution

The paper presents a new graph generation method based on tree decomposition, providing a reduced upper bound on decision complexity and a permutation invariant model for improved accuracy.

Findings

Superior performance on standard datasets

Reduced decision complexity in graph generation

Permutation invariant model effectiveness

Abstract

We propose TD-GEN, a graph generation framework based on tree decomposition, and introduce a reduced upper bound on the maximum number of decisions needed for graph generation. The framework includes a permutation invariant tree generation model which forms the backbone of graph generation. Tree nodes are supernodes, each representing a cluster of nodes in the graph. Graph nodes and edges are incrementally generated inside the clusters by traversing the tree supernodes, respecting the structure of the tree decomposition, and following node sharing decisions between the clusters. Finally, we discuss the shortcomings of standard evaluation criteria based on statistical properties of the generated graphs as performance measures. We propose to compare the performance of models based on likelihood. Empirical results on a variety of standard graph generation datasets demonstrate the superior performance of our method.