Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation
This addresses a critical bottleneck in generative modeling for discrete structures like graphs, offering a novel solution to compounding denoising errors.
The paper tackled the problem of error accumulation in discrete diffusion models for graph generation by proposing a Simple Iterative Denoising framework with a Critic, resulting in significant performance improvements over existing baselines.
Discrete Diffusion and Flow Matching models have significantly advanced generative modeling for discrete structures, including graphs. However, the dependencies between intermediate noisy states lead to error accumulation and propagation during the reverse denoising process - a phenomenon known as compounding denoising errors. To address this problem, we propose a novel framework called Simple Iterative Denoising, which simplifies discrete diffusion and circumvents the issue by assuming conditional independence between intermediate states. Additionally, we enhance our model by incorporating a Critic. During generation, the Critic selectively retains or corrupts elements in an instance based on their likelihood under the data distribution. Our empirical evaluations demonstrate that the proposed method significantly outperforms existing discrete diffusion baselines in graph generation tasks.