mlsanityData to 7 Oct 2026

Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing

arXiv 2210.15889 ↗First posted 28 Oct 2022cs.AI cs.CV cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and statistical paradigms of cognition, has been an active research area of Artificial Intelligence (AI) for many years. As NeSy shows promise of reconciling the advantages of reasoning and interpretability of symbolic representation and robust learning in neural networks, it may serve as a catalyst for the next generation of AI. In the present paper, we provide a systematic overview of the recent developments and important contributions of NeSy research. Firstly, we introduce study history of this area, covering early work and foundations. We further discuss background concepts and identify key driving factors behind the development of NeSy. Afterward, we categorize recent landmark approaches along several main characteristics that underline this research paradigm, including neural-symbolic integration, knowledge representation, knowledge embedding, and functionality. Next, we briefly discuss the successful application of modern NeSy approaches in several domains. Then, we benchmark several NeSy methods on three representative application tasks. Finally, we identify the open problems together with potential future research directions. This survey is expected to help new researchers enter this rapidly evolving field and accelerate the progress towards data-and knowledge-driven AI.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 138 of its 278 references that are in the map. First posted on arXiv 28 Oct 2022.

Builds on

138 of 278 references.

References · 138

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  5. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  6. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  7. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  8. 2019AI Feynman: a Physics-Inspired Method for Symbolic Regressioncited by 536
  9. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  10. 2015Neural Module Networkscited by 375
  11. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
  12. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 335
38 more
  1. 2019Analysing Mathematical Reasoning Abilities of Neural Modelscited by 331
  2. 2018Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understandingcited by 304
  3. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  4. 2019Deep Learning for Symbolic Mathematicscited by 266
  5. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  6. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  7. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 237
  8. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  9. 2018Deep Learning: A Critical Appraisalcited by 214
  10. 2017Learning Explanatory Rules from Noisy Datacited by 210
  11. 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 203
  12. 2020Logic Tensor Networkscited by 197
  13. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 195
  14. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 194
  15. 2020The Computational Limits of Deep Learningcited by 188
  16. 2021Neural Symbolic Regression that Scalescited by 185
  17. 2018Compositional Attention Networks for Machine Reasoningcited by 183
  18. 2017Learning to Plan Chemical Synthesescited by 175
  19. 2019SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solvercited by 173
  20. 2017End-to-End Differentiable Provingcited by 159
  21. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  22. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 149
  23. 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
  24. 2016DeepCoder: Learning to Write Programscited by 145
  25. 2019Neural Logic Machinescited by 144
  26. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  27. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  28. 2017Inferring and Executing Programs for Visual Reasoningcited by 130
  29. 2017Learning to Reason: End-to-End Module Networks for Visual Question Answeringcited by 125
  30. 2020KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQAcited by 124
  31. 2015Neural GPUs Learn Algorithmscited by 118
  32. 2019Learning by Abstraction: The Neural State Machinecited by 113
  33. 2019Making Better Mistakes: Leveraging Class Hierarchies with Deep Networkscited by 112
  34. 2014Learning to Executecited by 105
  35. 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
  36. 2018Explainable and Explicit Visual Reasoning over Scene Graphscited by 103
  37. 2020Retrosynthesis Prediction with Conditional Graph Logic Networkcited by 103
  38. 2022Semantic Probabilistic Layers for Neuro-Symbolic Learningcited by 103

50 most cited of 138 All 138 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 4; 2025: 12; 2026: 10.

34 papers.

Sort:

By area:

  1. 2024R2-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoningcited by 41
  2. 2023Logical Reasoning over Natural Language as Knowledge Representation: A Surveycited by 32
  3. 2023Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentationcited by 29
  4. 2023Towards Knowledge-driven Autonomous Drivingcited by 29
  5. 2023Neural-Logic Human-Object Interaction Detectioncited by 25
  6. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
  7. 2024Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AIcited by 24
  8. 2023LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoningcited by 17
  9. 2024A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligencecited by 10
  10. 2024Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generationcited by 10
  11. 2025A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directionscited by 7
  12. 2025A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectivescited by 5
22 more
  1. 2023Emergence and Function of Abstract Representations in Self-Supervised Transformerscited by 3
  2. 2025Echo Planning for Autonomous Driving: From Current Observations to Future Trajectories and Backcited by 3
  3. 2025A Conditional Probability Framework for Compositional Zero-shot Learningcited by 2
  4. 2025Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunitiescited by 2
  5. 2025Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineeringcited by 2
  6. 2025Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanationscited by 2
  7. 2025Standard Neural Computation Alone Is Insufficient for Logical Intelligencecited by 1
  8. 2025Composable Building Blocks for Controllable and Transparent Interactive AI Systemscited by 1
  9. 2025Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive Surveycited by 1
  10. 2026NeuroShield: A Neuro-Symbolic Framework for Adversarial Robustnesscited by 1
  11. 2026TEGRA: Text Encoding With Graph and Retrieval Augmentation for Misinformation Detectioncited by 1
  12. 2026Neural Decision-Propagation for Answer Set Programmingcited by 1
  13. 2026BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networkscited by 1
  14. 2022The Path to Autonomous Learnerscited by 0
  15. 2025Chemical knowledge-informed framework for privacy-aware retrosynthesis learningcited by 0
  16. 2025MATCH: Engineering Transparent and Controllable Conversational XAI Systems through Composable Building Blockscited by 0
  17. 2026Frequency-Corrupt Based Graph Self-Supervised Learningcited by 0
  18. 2026Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognitioncited by 0
  19. 2026Deep Arguingcited by 0
  20. 2026SMART: A Machine Learning and Monte Carlo Framework for Rapid Analysis of Stochastic Transistor Aging and Process Variation in Digital Circuitscited by 0
  21. 2026MedVA: An End-to-End Neuro-Symbolic Agentic System for Medical Volume Visualizationcited by 0
  22. 2026Prototype-Rule Neurosymbolic Regularization for Rank-Constrained Tensor Neural Networks under Label Scarcitycited by 0