# Solving Visual Analogies Using Neural Algorithmic Reasoning

arXiv: https://arxiv.org/abs/2111.10361 · HTML: https://mlsanity.com/paper/2111.10361/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 3 references that are in the map.
- First posted on arXiv 19 Nov 2021.

## Builds on (most cited first, 1 of 1)

- [Neural Algorithmic Reasoning](https://mlsanity.com/paper/2105.02761/) (2021)

## Built on by (most cited first, 1 of 1)

- [Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spaces](https://mlsanity.com/paper/2209.08750/) (2022)

## Abstract (arXiv)

We consider a class of visual analogical reasoning problems that involve discovering the sequence of transformations by which pairs of input/output images are related, so as to analogously transform future inputs. This program synthesis task can be easily solved via symbolic search. Using a variation of the `neural analogical reasoning' approach of (Velickovic and Blundell 2021), we instead search for a sequence of elementary neural network transformations that manipulate distributed representations derived from a symbolic space, to which input images are directly encoded. We evaluate the extent to which our `neural reasoning' approach generalizes for images with unseen shapes and positions.