arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.05596cs.LGstat.ML
收藏

从第一性原理出发的组合泛化

Compositional Generalization from First Principles

University of Tübingen(图宾根大学);Tübingen AI Center(图宾根人工智能中心);Max-Planck-Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Thaddäus Wiedemer, Prasanna Mayilvahanan, Matthias Bethge, Wieland Brendel

AI总结:

本文从数据生成过程的组合性出发,提出仅依赖训练分布支撑集与模型架构的充分条件,并通过真实场景与实验验证,为组合泛化建立第一性原理理论框架。

摘要:

利用我们世界的组合性质来加速学习并促进泛化,是人类感知的一个标志性特征。然而在机器学习中,即使对于具有显式组合先验的模型,实现组合泛化也被证明是一个难以捉摸的目标。为了更好地理解组合泛化,我们在此自底向上地研究它:受可辨识表示学习的启发,我们将组合性视为数据生成过程而非数据本身的一种属性。这一重新表述使我们能够仅针对训练分布的支撑集和模型架构推导出温和条件,而这些条件足以实现组合泛化。我们进一步展示了我们的理论框架如何应用于真实世界场景,并通过实验验证了我们的发现。我们的结果为组合泛化的原则性理论研究奠定了基础。

英文摘要:

Leveraging the compositional nature of our world to expedite learning and facilitate generalization is a hallmark of human perception. In machine learning, on the other hand, achieving compositional generalization has proven to be an elusive goal, even for models with explicit compositional priors. To get a better handle on compositional generalization, we here approach it from the bottom up: Inspired by identifiable representation learning, we investigate compositionality as a property of the data-generating process rather than the data itself. This reformulation enables us to derive mild conditions on only the support of the training distribution and the model architecture, which are sufficient for compositional generalization. We further demonstrate how our theoretical framework applies to real-world scenarios and validate our findings empirically. Our results set the stage for a principled theoretical study of compositional generalization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑