We introduce discriminator guidance in the setting of Autoregressive Diffusion Models. The use of a discriminator to guide a diffusion process has previously been used for continuous diffusion models, and in this work we derive ways of using a discriminator together with a pretrained generative model in the discrete case. First, we show that using an optimal discriminator will correct the pretrained model and enable exact sampling from the underlying data distribution. Second, to account for the realistic scenario of using a sub-optimal discriminator, we derive a sequential Monte Carlo algorithm which iteratively takes the predictions from the discrimiator into account during the generation process. We test these approaches on the task of generating molecular graphs and show how the discriminator improves the generative performance over using only the pretrained model.

翻译：我们在自回归扩散模型框架中引入了识别器引导机制。此前，利用识别器指导扩散过程的方法已应用于连续扩散模型，而本文则推导了在离散情形下将识别器与预训练生成模型结合使用的技术。首先，我们证明采用最优识别器能够修正预训练模型，从而从底层数据分布中精确采样。其次，针对实际场景中可能使用次优识别器的情况，我们推导了一种序列蒙特卡洛算法，该算法在生成过程中迭代性地将识别器的预测结果纳入考量。我们将这些方法应用于分子图生成任务，实验表明，相较于仅使用预训练模型，识别器能够显著提升生成性能。