mlsanityData to 14 Oct 2026

An Explicitly Relational Neural Network Architecture

arXiv 1905.10307 ↗First posted 24 May 2019cs.LG stat.MLcited by 35

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 10; 2023: 8; 2024: 7; 2025: 0; 2026: 1.

35 papers.

Sort:

By area:

  1. 2021Combinatorial optimization and reasoning with graph neural networkscited by 268
  2. 2022Object discovery and representation networkscited by 80
  3. 2021Tell me why! Explanations support learning relational and causal structurecited by 36
  4. 2022A Review of Emerging Research Directions in Abstract Visual Reasoningcited by 33
  5. 2022On Neural Architecture Inductive Biases for Relational Taskscited by 26
  6. 2023When can transformers reason with abstract symbols?cited by 24
  7. 2021Learning First-Order Representations for Planning from Black-Box States: New Resultscited by 23
  8. 2023Systematic Visual Reasoning through Object-Centric Relational Abstractioncited by 20
  9. 2021In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specificationscited by 17
  10. 2022ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Timecited by 16
  11. 2023Structure in Deep Reinforcement Learning: A Survey and Open Problemscited by 16
  12. 2024A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practicescited by 15
23 more
  1. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learningcited by 14
  2. 2021Algorithmic Concept-based Explainable Reasoningcited by 12
  3. 2023Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformerscited by 12
  4. 2024Slot Abstractors: Toward Scalable Abstract Visual Reasoningcited by 11
  5. 2021Faster-LTN: a neuro-symbolic, end-to-end object detection architecturecited by 10
  6. 2021pix2rule: End-to-end Neuro-symbolic Rule Learningcited by 9
  7. 2024Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecturecited by 7
  8. 2021Target Languages (vs. Inductive Biases) for Learning to Act and Plancited by 5
  9. 2024Disentangling and Integrating Relational and Sensory Information in Transformer Architecturescited by 5
  10. 2021Decomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrievalcited by 4
  11. 2023Associative Transformercited by 4
  12. 2024A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoningcited by 4
  13. 2022Sparse Relational Reasoning with Object-Centric Representationscited by 2
  14. 2023Learning Hierarchical Relational Representations through Relational Convolutionscited by 2
  15. 2022ViRel: Unsupervised Visual Relations Discovery with Graph-level Analogycited by 1
  16. 2022Deep set conditioned latent representations for action recognitioncited by 1
  17. 2023Lateralized Learning for Multi-Class Visual Classification Taskscited by 1
  18. 2023Bridging Neural and Symbolic Representations with Transitional Dictionary Learningcited by 1
  19. 2024LARS-VSA: A Vector Symbolic Architecture For Learning with Abstract Rulescited by 1
  20. 2022Language-Based Causal Representation Learningcited by 0
  21. 2022Functional Indirection Neural Estimator for Better Out-of-distribution Generalizationcited by 0
  22. 2022Relate to Predict: Towards Task-Independent Knowledge Representations for Reinforcement Learningcited by 0
  23. 2026Predictive Reasoning with Augmented Anomaly Contrastive Learning for Compositional Visual Relationscited by 0