mlsanityData to 7 Oct 2026

A simple neural network module for relational reasoning

arXiv 1706.01427 ↗First posted 5 Jun 2017cs.CL cs.LGcited by 345

Not on the map. Why?

Cited by 48 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation Networks (RNs) as a simple plug-and-play module to solve problems that fundamentally hinge on relational reasoning. We tested RN-augmented networks on three tasks: visual question answering using a challenging dataset called CLEVR, on which we achieve state-of-the-art, super-human performance; text-based question answering using the bAbI suite of tasks; and complex reasoning about dynamic physical systems. Then, using a curated dataset called Sort-of-CLEVR we show that powerful convolutional networks do not have a general capacity to solve relational questions, but can gain this capacity when augmented with RNs. Our work shows how a deep learning architecture equipped with an RN module can implicitly discover and learn to reason about entities and their relations.

Key facts. Cited by 345 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 3; 2020: 0; 2021: 101; 2022: 91; 2023: 63; 2024: 42; 2025: 28; 2026: 17.

345 papers.

Sort:

By area:

  1. 2021How Attentive are Graph Attention Networks?cited by 818
  2. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  3. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 776
  4. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  5. 2021Combinatorial optimization and reasoning with graph neural networkscited by 267
  6. 2021Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Modelscited by 244
  7. 2021GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoningcited by 224
  8. 2021Towards Causal Representation Learningcited by 207
  9. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  10. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answeringcited by 170
  11. 2022SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Modelscited by 146
  12. 2021Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Timecited by 140
38 more
  1. 2022UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expressioncited by 137
  2. 2023Representational Strengths and Limitations of Transformerscited by 132
  3. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  4. 2021Towards artificial general intelligence via a multimodal foundation modelcited by 112
  5. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  6. 2022Amortized Inference for Causal Structure Learningcited by 89
  7. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  8. 2021Coordination Among Neural Modules Through a Shared Global Workspacecited by 83
  9. 2022ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similaritycited by 82
  10. 2022Expander Graph Propagationcited by 75
  11. 2021Object-Region Video Transformerscited by 73
  12. 2021Directed Acyclic Graph Neural Networkscited by 70
  13. 2021A Survey on Interpretable Reinforcement Learningcited by 70
  14. 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
  15. 2022StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Textscited by 65
  16. 2021Universal Approximation of Functions on Setscited by 62
  17. 2021Visual Representation Learning Does Not Generalize Strongly Within the Same Domaincited by 60
  18. 2022Theory of Graph Neural Networks: Representation and Learningcited by 60
  19. 2023On the Connection Between MPNN and Graph Transformercited by 60
  20. 2023Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Textcited by 59
  21. 2024DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)cited by 56
  22. 2024From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Modelscited by 52
  23. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  24. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  25. 2022A Benchmark for Compositional Visual Reasoningcited by 43
  26. 2023Bi-directional Training for Composed Image Retrieval via Text Prompt Learningcited by 43
  27. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approachescited by 43
  28. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 41
  29. 2021JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answeringcited by 40
  30. 2022Complex-Valued Autoencoders for Object Discoverycited by 40
  31. 2021Discrete-Valued Neural Communicationcited by 39
  32. 2021Unified Graph Structured Models for Video Understandingcited by 38
  33. 2022OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphscited by 38
  34. 2022Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matricescited by 37
  35. 2022The Neural Race Reduction: Dynamics of Abstraction in Gated Networkscited by 37
  36. 2021Tell me why! Explanations support learning relational and causal structurecited by 36
  37. 2023Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encodercited by 35
  38. 2021Greedy Gradient Ensemble for Robust Visual Question Answeringcited by 34

50 most cited of 345 All 345 (JSON)