Large monolithic generative models trained on massive amounts of data have become an increasingly dominant approach in AI research. In this paper, we argue that we should instead construct large generative systems by composing smaller generative models together. We show how such a compositional generative approach enables us to learn distributions in a more data-efficient manner, enabling generalization to parts of the data distribution unseen at training time. We further show how this enables us to program and construct new generative models for tasks completely unseen at training. Finally, we show that in many cases, we can discover separate compositional components from data.

翻译：大规模单体生成模型在海量数据上训练已成为人工智能研究中日益主导的方法。在本文中，我们认为应当通过组合较小的生成模型来构建大型生成系统。我们展示了这种组合式生成方法如何以更高数据效率的方式学习分布，从而实现对训练阶段未见数据分布部分的泛化能力。进一步地，我们说明该方法如何能够针对训练时完全未见的新任务进行生成模型的编程与构建。最后，我们证明在许多情况下可以从数据中发现独立的组合式组件。