类比学习：面向组合泛化的因果框架
Learning by Analogy: A Causal Framework for Compositional Generalization
该论文提出的层级因果数据生成过程与可识别性理论，为视觉生成模型（如扩散模型）实现组合泛化提供了可证明的潜变量结构设计原则，可指导构建能重组已知概念生成新场景的生成器。
原文依据 we also prove that this latent hierarchical structure is provably recoverable (identifiable) from observable data like text-image pairs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论组合泛化——理解和生成已学习概念的新组合的能力——使模型能够将其能力扩展到有限经验之外。尽管这种能力有效，但实现这一关键能力的数据结构和原理仍知之甚少。我们提出，组合泛化从根本上要求将高层概念分解为基本的低层概念，这些低层概念可以在相似上下文中重新组合，类似于人类在概念之间进行类比的方式。例如，从未见过孔雀吃米饭的人可以通过将其与之前观察到的鸡吃米饭的场景联系起来来想象这一场景。在这项工作中，我们使用因果模块性和最小变化的原则形式化这些直观过程。我们引入了一个层级数据生成过程，该过程自然地编码了不同层次的概念及其交互机制。在理论上，我们证明了这种方法能够支持组合概念之间的复杂关系，从而实现组合泛化，超越了先前假设加性效应等简单交互的工作。关键的是，我们还证明了这种潜在层级结构可以从可观测数据（如文本-图像对）中可证明地恢复（可识别），这是学习此类生成过程的必要步骤。为了验证我们的理论，我们应用理论框架中的见解，并在基准数据集上取得了显著改进。
英文原文摘要 1505 字符
Compositional generalization -- the ability to understand and generate novel combinations of learned concepts -- enables models to extend their capabilities beyond limited experiences. While effective, the data structures and principles that enable this crucial capability remain poorly understood. We propose that compositional generalization fundamentally requires decomposing high-level concepts into basic, low-level concepts that can be recombined across similar contexts, similar to how humans draw analogies between concepts. For example, someone who has never seen a peacock eating rice can envision this scene by relating it to their previous observations of a chicken eating rice.In this work, we formalize these intuitive processes using principles of causal modularity and minimal changes. We introduce a hierarchical data-generating process that naturally encodes different levels of concepts and their interaction mechanisms. Theoretically, we demonstrate that this approach enables compositional generalization supporting complex relations between composed concepts, advancing beyond prior work that assumes simpler interactions like additive effects. Critically, we also prove that this latent hierarchical structure is provably recoverable (identifiable) from observable data like text-image pairs, a necessary step for learning such a generative process. To validate our theory, we apply insights from our theoretical framework and achieve significant improvements on benchmark datasets.