When does compositional structure yield compositional generalization? A kernel theory.
Keywords: compositional generalization, rule learning, kernel regression, kernel models, relational reasoning, memorization, shortcuts, dataset statistics, norm minimization, implicit regularization, disentanglement
TL;DR: We present a theory of compositional generalization in kernel models with fixed representations and validate it in deep neural networks.
Abstract: Compositional generalization (the ability to respond correctly to novel combinations of familiar components) is thought to be a cornerstone of intelligent behavior. Compositionally structured (e.g. disentangled) representations are essential for this; however, the conditions under which they yield compositional generalization remain unclear. To address this gap, we present a general theory of compositional generalization in kernel models with fixed, compositionally structured representations, a tractable framework for characterizing the impact of dataset statistics on generalization. We find that these models are constrained to adding up values assigned to each combination of components seen during training ("conjunction-wise additivity"). This imposes fundamental restrictions on the set of tasks compositionally structured kernel models can learn, in particular preventing them from transitively generalizing equivalence relations. Even for compositional tasks that they can in principle learn, we identify novel failure modes in compositional generalization that arise from biases in the training data and affect important compositional building blocks such as symbolic addition and context dependence (memorization leak and shortcut bias). Finally, we empirically validate our theory, showing that it captures the behavior of deep neural networks (convolutional networks, residual networks, and Vision Transformers) trained on a set of compositional tasks with similarly structured data. Ultimately, this work provides a theoretical perspective on how statistical structure in the training data can affect compositional generalization, with implications for how to identify and remedy failure modes in deep learning models.
Primary Area: learning theory
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 12476
Loading