mlsanityData to 7 Oct 2026

A Survey on Neural-symbolic Learning Systems

arXiv 2111.08164 ↗First posted 10 Nov 2021cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence. However, they have been found to lack effective reasoning and cognitive ability. On the other hand, symbolic systems exhibit exceptional cognitive intelligence but suffer from poor learning capabilities when compared to neural systems. Recognizing the advantages and disadvantages of both methodologies, an ideal solution emerges: combining neural systems and symbolic systems to create neural-symbolic learning systems that possess powerful perception and cognition. The purpose of this paper is to survey the advancements in neural-symbolic learning systems from four distinct perspectives: challenges, methods, applications, and future directions. By doing so, this research aims to propel this emerging field forward, offering researchers a comprehensive and holistic overview. This overview will not only highlight the current state-of-the-art but also identify promising avenues for future research.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 70 of its 152 references that are in the map. First posted on arXiv 10 Nov 2021.

Builds on

70 of 152 references.

References · 70

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  4. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  5. 2016Complex Embeddings for Simple Link Predictioncited by 897
  6. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  7. 2015Gated Graph Sequence Neural Networkscited by 792
  8. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  9. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  10. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  11. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  12. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
38 more
  1. 2015Neural Module Networkscited by 375
  2. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
  3. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 321
  4. 2018Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understandingcited by 304
  5. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  6. 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 265
  7. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  8. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 237
  9. 2017Learning Explanatory Rules from Noisy Datacited by 210
  10. 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 203
  11. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 195
  12. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 194
  13. 2018Compositional Attention Networks for Machine Reasoningcited by 183
  14. 2017End-to-End Differentiable Provingcited by 159
  15. 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
  16. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 149
  17. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  18. 2019Learning by Abstraction: The Neural State Machinecited by 113
  19. 2016Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervisioncited by 101
  20. 2020Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspectivecited by 93
  21. 2017Logic Tensor Networks for Semantic Image Interpretationcited by 92
  22. 2018Rethinking Knowledge Graph Propagation for Zero-Shot Learningcited by 87
  23. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  24. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 77
  25. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  26. 2019Probabilistic Logic Neural Networks for Reasoningcited by 69
  27. 2019Neural Module Networks for Reasoning over Textcited by 65
  28. 2015Hinge-Loss Markov Random Fields and Probabilistic Soft Logiccited by 63
  29. 2017Thinking Fast and Slow: Optimization Decomposition Across Timescalescited by 60
  30. 2018Learning to Solve NP-Complete Problems - A Graph Neural Network for Decision TSPcited by 58
  31. 2018PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Makingcited by 51
  32. 2020Efficient Probabilistic Logic Reasoning with Graph Neural Networkscited by 50
  33. 2019Embedding Symbolic Knowledge into Deep Networkscited by 49
  34. 2019Learning to Infer Program Sketchescited by 44
  35. 2016Towards Deep Symbolic Reinforcement Learningcited by 42
  36. 2018Neural-Guided Deductive Search for Real-Time Program Synthesis from Examplescited by 39
  37. 2019Learn to Explain Efficiently via Neural Logic Inductive Learningcited by 38
  38. 2016Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networkscited by 37

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 14; 2025: 17; 2026: 5.

39 papers.

Sort:

By area:

  1. 2024Distilling System 2 into System 1cited by 152
  2. 2025Neuro-Symbolic AI in 2024: A Systematic Reviewcited by 36
  3. 2025T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generationcited by 35
  4. 2025Explain Before You Answer: A Survey on Compositional Visual Reasoningcited by 26
  5. 2024SymbolicAI: A framework for logic-based approaches combining generative models and solverscited by 15
  6. 2024A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligencecited by 10
  7. 2024Weakly Supervised Anomaly Detection via Knowledge-Data Alignmentcited by 10
  8. 2024From Frege to chatGPT: Compositionality in language, cognition, and deep neural networkscited by 7
  9. 2024Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answeringcited by 6
  10. 2024Neurosymbolic Graph Enrichment for Grounded World Modelscited by 6
  11. 2025Position: Foundation Models for Tabular Data within Systemic Contexts Need Groundingcited by 5
  12. 2023Augmenting deep neural networks with symbolic knowledge: Towards trustworthy and interpretable AI for educationcited by 4
27 more
  1. 2024Take A Step Back: Rethinking the Two Stages in Visual Reasoningcited by 4
  2. 2025A Smooth Transition Between Induction and Deduction: Fast Abductive Learning Based on Probabilistic Symbol Perceptioncited by 3
  3. 2025Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neurosciencecited by 3
  4. 2025SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discoverycited by 3
  5. 2026Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AIcited by 3
  6. 2024Multi-Excitation Projective Simulation with a Many-Body Physics Inspired Inductive Biascited by 2
  7. 2024A Synergistic Approach In Network Intrusion Detection By Neurosymbolic AIcited by 2
  8. 2024CiteFusion: An Ensemble Framework for Citation Intent Classification Harnessing Dual-Model Binary Couples and SHAP Analysescited by 2
  9. 2025From Understanding the World to Intervening in It: A Unified Multi-Scale Framework for Embodied Cognitioncited by 2
  10. 2025Enhancing Symbolic Machine Learning by Subsymbolic Representationscited by 2
  11. 2025Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learningcited by 2
  12. 2025Neural Logic Networks for Interpretable Classificationcited by 2
  13. 2023Towards Commonsense Knowledge based Fuzzy Systems for Supporting Size-Related Fine-Grained Object Detectioncited by 1
  14. 2024Synergizing Machine Learning & Symbolic Methods: A Survey on Hybrid Approaches to Natural Language Processingcited by 1
  15. 2024A Survey on the Integration of Generative AI for Critical Thinking in Mobile Networkscited by 1
  16. 2024Context-aware knowledge graph framework for traffic speed forecasting using graph neural networkcited by 1
  17. 2025Verification Learning: Make Unsupervised Neuro-Symbolic System Feasiblecited by 1
  18. 2025A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Datacited by 1
  19. 2025Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive Surveycited by 1
  20. 2026Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Frameworkcited by 1
  21. 2026From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontiercited by 1
  22. 2023A Brain-Inspired Sequence Learning Model based on a Logiccited by 0
  23. 2025Neuro-Symbolic Scene Graph Conditioning for Synthetic Image Dataset Generationcited by 0
  24. 2025Physics-Inspired Spatial Temporal Graph Neural Networks for Predicting Industrial Chain Resiliencecited by 0
  25. 2025NASP-T: A Fuzzy Neuro-Symbolic Transformer for Logic-Constrained Aviation Safety Report Classificationcited by 0
  26. 2026Modeling Endogenous Logic: Causal Neuro-Symbolic Reasoning Model for Explainable Multi-Behavior Recommendationcited by 0
  27. 2026Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Datacited by 0