# Solving Raven's Progressive Matrices with Multi-Layer Relation Networks

arXiv: https://arxiv.org/abs/2003.11608 · HTML: https://mlsanity.com/paper/2003.11608/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2020.

## Built on by (most cited first, 16 of 16)

- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices](https://mlsanity.com/paper/2203.04571/) (2022)
- [Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices](https://mlsanity.com/paper/2201.12382/) (2022)
- [A Review of Emerging Research Directions in Abstract Visual Reasoning](https://mlsanity.com/paper/2202.10284/) (2022)
- [Effective Abstract Reasoning with Dual-Contrast Network](https://mlsanity.com/paper/2205.13720/) (2022)
- [Learning to reason over visual objects](https://mlsanity.com/paper/2303.02260/) (2023)
- [Slot Abstractors: Toward Scalable Abstract Visual Reasoning](https://mlsanity.com/paper/2403.03458/) (2024)
- [Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices](https://mlsanity.com/paper/2303.11730/) (2023)
- [Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems](https://mlsanity.com/paper/2307.07734/) (2023)
- [A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processing](https://mlsanity.com/paper/2309.10532/) (2023)
- [Learning Visual Abstract Reasoning through Dual-Stream Networks](https://mlsanity.com/paper/2411.19451/) (2024)
- [Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection](https://mlsanity.com/paper/2401.09966/) (2024)
- [Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecture](https://mlsanity.com/paper/2501.11896/) (2025)
- [Deep Non-Monotonic Reasoning for Visual Abstract Reasoning Tasks](https://mlsanity.com/paper/2302.07137/) (2023)
- [The minimal computational substrate of fluid intelligence](https://mlsanity.com/paper/2308.07039/) (2023)
- [A Feature-based Generalizable Prediction Model for Both Perceptual and Abstract Reasoning](https://mlsanity.com/paper/2403.05641/) (2024)

## Abstract (arXiv)

Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.