Permutation-invariant Autoregressive Diffusion for Graph Generation

Graph generation has been dominated by autoregressive models due to their simplicity and effectiveness, despite their sensitivity to node ordering. Diffusion models, on the other hand, have garnered increasing attention as they offer comparable performance while being permutation-invariant. Current graph diffusion models generate graphs in a one-shot fashion, however they require extra features and thousands of denoising steps to achieve optimal performance.