Graph Generation with $K^2$-trees
This addresses graph generation challenges in domains like drug discovery and social network analysis, presenting a novel but incremental approach.
The paper tackles graph generation from target distributions by introducing a method using K²-tree representation with a Transformer-based architecture, achieving superior performance on six datasets including molecular graphs.
Generating graphs from a target distribution is a significant challenge across many domains, including drug discovery and social network analysis. In this work, we introduce a novel graph generation method leveraging $K^2$-tree representation, originally designed for lossless graph compression. The $K^2$-tree representation {encompasses inherent hierarchy while enabling compact graph generation}. In addition, we make contributions by (1) presenting a sequential $K^2$-treerepresentation that incorporates pruning, flattening, and tokenization processes and (2) introducing a Transformer-based architecture designed to generate the sequence by incorporating a specialized tree positional encoding scheme. Finally, we extensively evaluate our algorithm on four general and two molecular graph datasets to confirm its superiority for graph generation.