A theory of relation learning and cross-domain generalization

Leonidas A A Doumas*, Guillermo Puebla Ramírez, Andrea E. Martin, John E. Hummel

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

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 (Hummel & Holyoak, 1997, 2003) and DORA (Doumas, Hummel, & Sandhofer, 2008) 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.
Original languageEnglish
JournalPsychological Review
Early online date4 Feb 2022
Publication statusE-pub ahead of print - 4 Feb 2022

Keywords / Materials (for Non-textual outputs)

  • relation learning
  • generalization
  • learning relational content
  • learning structured representations
  • neural oscillations


Dive into the research topics of 'A theory of relation learning and cross-domain generalization'. Together they form a unique fingerprint.

Cite this