mlsanityData to 7 Oct 2026

Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey

arXiv 2302.07200 ↗First posted 14 Feb 2023cs.AI cs.LO stat.MLcited by 21

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Neurosymbolic AI is an increasingly active area of research that combines symbolic reasoning methods with deep learning to leverage their complementary benefits. As knowledge graphs are becoming a popular way to represent heterogeneous and multi-relational data, methods for reasoning on graph structures have attempted to follow this neurosymbolic paradigm. Traditionally, such approaches have utilized either rule-based inference or generated representative numerical embeddings from which patterns could be extracted. However, several recent studies have attempted to bridge this dichotomy to generate models that facilitate interpretability, maintain competitive performance, and integrate expert knowledge. Therefore, we survey methods that perform neurosymbolic reasoning tasks on knowledge graphs and propose a novel taxonomy by which we can classify them. Specifically, we propose three major categories: (1) logically-informed embedding approaches, (2) embedding approaches with logical constraints, and (3) rule learning approaches. Alongside the taxonomy, we provide a tabular overview of the approaches and links to their source code, if available, for more direct comparison. Finally, we discuss the unique characteristics and limitations of these methods, then propose several prospective directions toward which this field of research could evolve.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 77 of its 202 references that are in the map. First posted on arXiv 14 Feb 2023.

Builds on

77 of 202 references.

References · 77

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  9. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  10. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  11. 2016Complex Embeddings for Simple Link Predictioncited by 897
  12. 2018Link Prediction Based on Graph Neural Networkscited by 829
38 more
  1. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  2. 2018Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Networkcited by 415
  3. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  4. 2020A Survey on Neural Network Interpretabilitycited by 291
  5. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  6. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 264
  7. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  8. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  9. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  10. 2019DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphscited by 173
  11. 2020Embedding-based Retrieval in Facebook Searchcited by 155
  12. 2018Embedding Logical Queries on Knowledge Graphscited by 120
  13. 2020Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challengescited by 120
  14. 2020Logical Neural Networkscited by 118
  15. 2021PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Modelscited by 118
  16. 2020RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphscited by 117
  17. 2020Interventional Few-Shot Learningcited by 112
  18. 2022Semantic Probabilistic Layers for Neuro-Symbolic Learningcited by 103
  19. 2020Complex Query Answering with Neural Link Predictorscited by 98
  20. 2020Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspectivecited by 93
  21. 2019Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphscited by 73
  22. 2019Probabilistic Logic Neural Networks for Reasoningcited by 69
  23. 2020Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networkscited by 64
  24. 2019Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoningcited by 63
  25. 2019Few-Shot Knowledge Graph Completioncited by 63
  26. 2020Interpretability and Explainability: A Machine Learning Zoo Mini-tourcited by 55
  27. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  28. 2022Oversquashing in GNNs through the lens of information contraction and graph expansioncited by 52
  29. 2017Knowledge Graph Embedding with Iterative Guidance from Soft Rulescited by 51
  30. 2020Efficient Probabilistic Logic Reasoning with Graph Neural Networkscited by 50
  31. 2020Neural-Symbolic Integration: A Compositional Perspectivecited by 45
  32. 2020Turning 30: New Ideas in Inductive Logic Programmingcited by 42
  33. 2021ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregationcited by 39
  34. 2021Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Conceptscited by 37
  35. 2018Improving Knowledge Graph Embedding Using Simple Constraintscited by 36
  36. 2020Drug Repurposing for COVID-19 via Knowledge Graph Completioncited by 30
  37. 2016TensorLog: A Differentiable Deductive Databasecited by 29
  38. 2019Neural Markov Logic Networkscited by 27

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 8; 2026: 6.

21 papers.

Sort:

By area:

  1. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  2. 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databasescited by 35
  3. 2025AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPOcited by 33
  4. 2024Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agentscited by 9
  5. 2024Neuro-Symbolic Entity Alignment via Variational Inferencecited by 8
  6. 2025A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Realitycited by 8
  7. 2025Position: Foundation Models for Tabular Data within Systemic Contexts Need Groundingcited by 5
  8. 2023Neurosymbolic AI for Reasoning on Biomedical Knowledge Graphscited by 4
  9. 2025CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineeringcited by 3
  10. 2023Knowledge Enhanced Graph Neural Networks for Graph Completioncited by 2
  11. 2024Prompt-Time Ontology-Driven Symbolic Knowledge Capture with Large Language Modelscited by 2
  12. 2024MARS: A neurosymbolic approach for interpretable drug discoverycited by 2
9 more
  1. 2025Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunitiescited by 2
  2. 2025Ontology-Enhanced Knowledge Graph Completion using Large Language Modelscited by 1
  3. 2025DeepGraphLog for Layered Neurosymbolic AIcited by 1
  4. 2026Do we have the knowledge we need? Rethinking human-AI decision-making in corporationscited by 0
  5. 2026Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prologcited by 0
  6. 2026Neuro-Symbolic Participation Governance for Verifiable AI Agents in Open Digital Twin Ecosystemscited by 0
  7. 2026Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Modelscited by 0
  8. 2026Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspectivecited by 0
  9. 2026Prototype-Rule Neurosymbolic Regularization for Rank-Constrained Tensor Neural Networks under Label Scarcitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Unified Neurosymbolic Reasoning on Knowledge Graphs
  2. 2025Reasoning in Neurosymbolic AI
  3. 2026The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning
  4. 2024Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective
  5. 2025A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning
  6. 2026NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering
  7. 2025Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations
  8. 2024Improving Neural-based Classification with Logical Background Knowledge