Score-based Models with Constraint
Recently a new class of generative models has become popularly called the score-based model. Rather than directly maximizing the log- likelihood of the density function, it models the score of the data to avoid explicitly calculating the normalizing constants. However, the current score-based model needs to fully consider the raw data property (e.g., molecule valency property ), which may generate sub-optimal samples. In this work, we propose a constrained score model by adding pre-designed sufficient statistics to the model so that it can guide the learning of the score model.
Please join meeting in Cummings #265.