A Theory of Relation Learning and Cross-domain Generalization

TL;DR

This paper introduces a computational model based on structured relational representations that can learn from non-relational inputs and generalize across domains through analogical inference, mirroring human reasoning and development.

Contribution

It extends existing relational inference models to enable zero-shot cross-domain generalization using learned structured representations without supervision.

Findings

Model learns relational structures from visual stimuli.

Enables zero-shot transfer between video games and psychological tasks.

Mirrors children's developmental reasoning trajectories.

Abstract

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.