# An Explicitly Relational Neural Network Architecture

arXiv: https://arxiv.org/abs/1905.10307 · HTML: https://mlsanity.com/paper/1905.10307/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

## Built on by (most cited first, 30 of 35)

- [Combinatorial optimization and reasoning with graph neural networks](https://mlsanity.com/paper/2102.09544/) (2021)
- [Object discovery and representation networks](https://mlsanity.com/paper/2203.08777/) (2022)
- [Tell me why! Explanations support learning relational and causal structure](https://mlsanity.com/paper/2112.03753/) (2021)
- [A Review of Emerging Research Directions in Abstract Visual Reasoning](https://mlsanity.com/paper/2202.10284/) (2022)
- [On Neural Architecture Inductive Biases for Relational Tasks](https://mlsanity.com/paper/2206.05056/) (2022)
- [When can transformers reason with abstract symbols?](https://mlsanity.com/paper/2310.09753/) (2023)
- [Learning First-Order Representations for Planning from Black-Box States: New Results](https://mlsanity.com/paper/2105.10830/) (2021)
- [Systematic Visual Reasoning through Object-Centric Relational Abstraction](https://mlsanity.com/paper/2306.02500/) (2023)
- [In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications](https://mlsanity.com/paper/2110.09461/) (2021)
- [ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time](https://mlsanity.com/paper/2206.15049/) (2022)
- [Structure in Deep Reinforcement Learning: A Survey and Open Problems](https://mlsanity.com/paper/2306.16021/) (2023)
- [A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices](https://mlsanity.com/paper/2406.08787/) (2024)
- [BlendRL: A Framework for Merging Symbolic and Neural Policy Learning](https://mlsanity.com/paper/2410.11689/) (2024)
- [Algorithmic Concept-based Explainable Reasoning](https://mlsanity.com/paper/2107.07493/) (2021)
- [Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers](https://mlsanity.com/paper/2304.00195/) (2023)
- [Slot Abstractors: Toward Scalable Abstract Visual Reasoning](https://mlsanity.com/paper/2403.03458/) (2024)
- [Faster-LTN: a neuro-symbolic, end-to-end object detection architecture](https://mlsanity.com/paper/2107.01877/) (2021)
- [pix2rule: End-to-end Neuro-symbolic Rule Learning](https://mlsanity.com/paper/2106.07487/) (2021)
- [Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture](https://mlsanity.com/paper/2409.13153/) (2024)
- [Target Languages (vs. Inductive Biases) for Learning to Act and Plan](https://mlsanity.com/paper/2109.07195/) (2021)
- [Disentangling and Integrating Relational and Sensory Information in Transformer Architectures](https://mlsanity.com/paper/2405.16727/) (2024)
- [Decomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrieval](https://mlsanity.com/paper/2103.12328/) (2021)
- [Associative Transformer](https://mlsanity.com/paper/2309.12862/) (2023)
- [A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning](https://mlsanity.com/paper/2406.11061/) (2024)
- [Sparse Relational Reasoning with Object-Centric Representations](https://mlsanity.com/paper/2207.07512/) (2022)
- [Learning Hierarchical Relational Representations through Relational Convolutions](https://mlsanity.com/paper/2310.03240/) (2023)
- [ViRel: Unsupervised Visual Relations Discovery with Graph-level Analogy](https://mlsanity.com/paper/2207.00590/) (2022)
- [Deep set conditioned latent representations for action recognition](https://mlsanity.com/paper/2212.11030/) (2022)
- [Lateralized Learning for Multi-Class Visual Classification Tasks](https://mlsanity.com/paper/2301.12637/) (2023)
- [Bridging Neural and Symbolic Representations with Transitional Dictionary Learning](https://mlsanity.com/paper/2308.02000/) (2023)

## Abstract (arXiv)

With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data. In order to evaluate and analyse the architecture, we introduce a family of simple visual relational reasoning tasks of varying complexity. We show that the proposed architecture, when pre-trained on a curriculum of such tasks, learns to generate reusable representations that better facilitate subsequent learning on previously unseen tasks when compared to a number of baseline architectures. The workings of a successfully trained model are visualised to shed some light on how the architecture functions.