TD-GEN: Graph Generation With Tree Decomposition
This work addresses graph generation for machine learning applications, but appears incremental as it builds on existing tree decomposition methods.
The authors tackled the problem of graph generation by proposing TD-GEN, a framework based on tree decomposition that reduces the maximum number of decisions needed, and demonstrated superior performance on standard datasets.
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.