Learning to Make Analogies by Contrasting Abstract Relational Structure

By Felix Hill, Adam Santoro, David G. T. Barrett, Ari S. Morcos, Timothy P. Lillicrap. 2019

117 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

In Cognitive Science & Psychology

Citations in the corpus

On the Binding Problem in Artificial Neural Networks (2020, background): “These failures at systematically reusing knowledge suggest that neural networks do not learn a compositional knowledge representation (although some mitigation is possible (Hill et al., 2019, 2020)).”
Are Disentangled Representations Helpful for Abstract Visual Reasoning? (2019, background): “Rather than focusing on a simple single factor classification task, we evaluate the usefulness of disentangled representations on abstract visual reasoning tasks that challenge the current capabilities of state-of-the-art deep neural networks [30, 65].”
A modeling framework for adaptive lifelong learning with transfer and savings through gating in the prefrontal cortex (2020, background): “This form of transfer learning is reminiscent of “learning by analogy,” a learning skill humans are very good at, but machines continue to struggle with [31],[32].”
Transforming task representations to perform novel tasks (2020, background): “These careful contrasts can encourage neural networks to extract more general concepts (19).”
Selective Replay Enhances Learning in Online Continual Analogical Reasoning (2021, background): “While humans have strong abstract reasoning abilities, neural networks struggle with these problems [37, 38, 70, 72, 86].”
Stratified Rule-Aware Network for Abstract Visual Reasoning (2020, unknown): “This type of back-door solutions is quite hidden and has also been discussed in other relational reasoning benchmarks, such as Visual Question Answering (VQA) (Johnson et al. 2017) and symbolic analogy (Hill et al. 2019).”
Visual Prompting via Image Inpainting (2022, background): “Predicting the correct completion was previously modeled as a classiﬁcation problem [43, 23], and other works have explored analogies in the context of learning different transformations between pairs of images [34, 46].”