# A Theory of Relation Learning and Cross-domain Generalization

arXiv: https://arxiv.org/abs/1910.05065 · HTML: https://mlsanity.com/paper/1910.05065/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2019.

## Built on by (most cited first, 11 of 11)

- [TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12514/) (2024)
- [Probabilistic Analogical Mapping with Semantic Relation Networks](https://mlsanity.com/paper/2103.16704/) (2021)
- [Can Large Language Models generalize analogy solving like children can?](https://mlsanity.com/paper/2411.02348/) (2024)
- [Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey](https://mlsanity.com/paper/2506.04461/) (2025)
- [Memory-Inspired Temporal Prompt Interaction for Text-Image Classification](https://mlsanity.com/paper/2401.14856/) (2024)
- [Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach](https://mlsanity.com/paper/2402.12675/) (2024)
- [Learning to Play Video Games with Intuitive Physics Priors](https://mlsanity.com/paper/2409.13886/) (2024)
- [Few-Shot Learning of Visual Compositional Concepts through Probabilistic Schema Induction](https://mlsanity.com/paper/2505.09859/) (2025)
- [From Basic Affordances to Symbolic Thought: A Computational Phylogenesis of Biological Intelligence](https://mlsanity.com/paper/2508.15082/) (2025)
- [Learning Rules from Rewards](https://mlsanity.com/paper/2203.13599/) (2022)
- [AIGenC: An AI generalisation model via creativity](https://mlsanity.com/paper/2205.09738/) (2022)

## Abstract (arXiv)

People readily generalize knowledge to novel domains and stimuli. We present a theory, instantiated in a computational model, based on the idea that cross-domain generalization in humans is a case of analogical inference over structured (i.e., symbolic) relational representations. The model is an extension of the LISA and DORA models of relational inference and learning. The resulting model learns both the content and format (i.e., structure) of relational representations from non-relational inputs without supervision, when augmented with the capacity for reinforcement learning, leverages these representations to learn individual domains, and then generalizes to new domains on the first exposure (i.e., zero-shot learning) via analogical inference. We demonstrate the capacity of the model to learn structured relational representations from a variety of simple visual stimuli, and to perform cross-domain generalization between video games (Breakout and Pong) and between several psychological tasks. We demonstrate that the model's trajectory closely mirrors the trajectory of children as they learn about relations, accounting for phenomena from the literature on the development of children's reasoning and analogy making. The model's ability to generalize between domains demonstrates the flexibility afforded by representing domains in terms of their underlying relational structure, rather than simply in terms of the statistical relations between their inputs and outputs.