構成可能な生成モデリング：単一モデルだけでは不十分
Compositional Generative Modeling: A Single Model is Not All You Need
大規模単一生成モデルではなく、小さな生成モデルを組み合わせて構成する手法を提案し、データ効率や未見分布への汎化、新タスクへのプログラム的構築が可能であることを示した。
著者: Yilun Du, Leslie Kaelbling
分類: cs.LG, cs.AI, cs.CV, cs.RO
原文アブストラクト
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.
