扩散模型处理离散任务新方法
Let It Go or Learn to Self-Correct: Continuous Diffusion for Constrained Discrete Tasks
扩散模型在Sudoku等离散任务表现提升,直接采样+自纠正训练让错误率大幅下降。
研究人员提出连续扩散模型处理离散任务的新方法。在Sudoku任务中,直接从模型清洁预测采样使有效性从31%提升至95%。研究引入自纠正训练,提高模型对推理错误的鲁棒性。扩散模型可学习非平凡全局约束,但需训练与推理更好对齐。
Let It Go or Learn to Self-Correct: Continuous Diffusion for Constrained Discrete Tasks
Denoising Diffusion Probabilistic Models (DDPMs) generate samples by starting from noise and repeatedly denoising while keeping each update close to the current noisy state. This behavior is effective in many continuous domains, but its role is less clear for globally constrained discrete tasks, such as Sudoku, graph connectivity, Latin squares, and N-queens. In such settings, early discrete errors can be difficult to undo. As a result, standard diffusion sampling may preserve early mistakes, even when the model's clean predictions are informative. We compare standard samplers to sampling directly from the model's clean prediction. Without retraining, this single change improves Sudoku validity from 31% to 95%, with consistent gains across the other discrete tasks. We hypothesize that staying close to the current noisy state is harmful because the reverse trajectory can drift off the forward noising distribution the model was trained on. To reduce this train-test mismatch, we further introduce self-correction training, which exposes the model to its own predictions, improving robustness to errors that arise during inference. This substantially improves the performance of standard samplers. Our results suggest that continuous diffusion models can learn nontrivial global constraints, but discrete reasoning tasks require better alignment between training and inference: either through samplers that reduce commitment to early decisions, or through training that teaches the model to correct its own inference-time errors.