Learning to Make Analogies by Contrasting Abstract Relational Structure

Abstract

Analogical reasoning has been a principal focus of various waves of AI research. Analogy is particularly challenging for machines because it requires relational structures to be represented such that they can be flexibly applied across diverse domains of experience. Here, we study how analogical reasoning can be induced in neural networks that learn to perceive and reason about raw visual data. We find that the critical factor for inducing such a capacity is not an elaborate architecture, but rather, careful attention to the choice of data and the manner in which it is presented to the model. The most robust capacity for analogical reasoning is induced when networks learn analogies by contrasting abstract relational structures in their input domains, a training method that uses only the input data to force models to learn about important abstract features. Using this technique we demonstrate capacities for complex, visual and symbolic analogy making and generalisation in even the simplest neural network architectures.

References in corpus (3)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• A simple neural network module for relational reasoning
• Generative Adversarial Active Learning

Cited by in corpus (16)

• Abstraction and Analogy-Making in Artificial Intelligence
• Are Disentangled Representations Helpful for Abstract Visual Reasoning?
• Multi-Label Contrastive Learning for Abstract Visual Reasoning
• Human-like generalization in a machine through predicate learning
• A Theory of Relation Learning and Cross-domain Generalization
• Transforming task representations to perform novel tasks
• Visual analogy: Deep learning versus compositional models
• CURI: A Benchmark for Productive Concept Learning Under Uncertainty
• One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems
• The relational processing limits of classic and contemporary neural network models of language processing
• Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
• Modeling Gestalt Visual Reasoning on the Raven's Progressive Matrices Intelligence Test Using Generative Image Inpainting Techniques
• Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning
• A Memory-Augmented Neural Network Model of Abstract Rule Learning
• Toward Building Science Discovery Machines
• Naive Artificial Intelligence