论文标题
图形结构化扩散模型
Graphically Structured Diffusion Models
论文作者
论文摘要
我们引入了一个框架，用于自动定义和学习具有特定于问题的结构的深层生成模型。我们解决了传统上通过算法（例如分类，对Sudoku的约束满意度和矩阵分解）来解决的问题领域。具体而言，我们使用针对问题规范量身定制的架构来训练扩散模型。此问题规范应包含描述变量之间关系的图形模型，并且通常会受益于子分组的明确表示。置换式不可分割也可以被利用。在各种实验中，我们就训练时间和最终准确性都改善了问题维度与模型的性能之间的缩放关系。我们的代码可以在https://github.com/plai-group/gsdm上找到。
We introduce a framework for automatically defining and learning deep generative models with problem-specific structure. We tackle problem domains that are more traditionally solved by algorithms such as sorting, constraint satisfaction for Sudoku, and matrix factorization. Concretely, we train diffusion models with an architecture tailored to the problem specification. This problem specification should contain a graphical model describing relationships between variables, and often benefits from explicit representation of subcomputations. Permutation invariances can also be exploited. Across a diverse set of experiments we improve the scaling relationship between problem dimension and our model's performance, in terms of both training time and final accuracy. Our code can be found at https://github.com/plai-group/gsdm.
