mlsanityData to 7 Oct 2026

A Critical Review of Inductive Logic Programming Techniques for Explainable AI

arXiv 2112.15319 ↗First posted 31 Dec 2021cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption. To instill confidence and trust in artificial intelligence systems, Explainable Artificial Intelligence has emerged as a response to improving modern machine learning algorithms' explainability. Inductive Logic Programming (ILP), a subfield of symbolic artificial intelligence, plays a promising role in generating interpretable explanations because of its intuitive logic-driven framework. ILP effectively leverages abductive reasoning to generate explainable first-order clausal theories from examples and background knowledge. However, several challenges in developing methods inspired by ILP need to be addressed for their successful application in practice. For example, existing ILP systems often have a vast solution space, and the induced solutions are very sensitive to noises and disturbances. This survey paper summarizes the recent advances in ILP and a discussion of statistical relational learning and neural-symbolic algorithms, which offer synergistic views to ILP. Following a critical review of the recent advances, we delineate observed challenges and highlight potential avenues of further ILP-motivated research toward developing self-explanatory artificial intelligence systems.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 36 of its 123 references that are in the map. First posted on arXiv 31 Dec 2021.

Builds on

36 of 123 references.

References · 36

  1. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  2. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  3. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
  4. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  5. 2019Deep Learning for Symbolic Mathematicscited by 266
  6. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  7. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 237
  8. 2017Learning Explanatory Rules from Noisy Datacited by 210
  9. 2017End-to-End Differentiable Provingcited by 159
  10. 2017Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphscited by 149
  11. 2019Neural Logic Machinescited by 144
  12. 2017RobustFill: Neural Program Learning under Noisy I/Ocited by 124
24 more
  1. 2020Inductive logic programming at 30: a new introductioncited by 83
  2. 2020Compositional Generalization via Neural-Symbolic Stack Machinescited by 80
  3. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 77
  4. 2020Learning programs by learning from failurescited by 73
  5. 2020From Statistical Relational to Neuro-Symbolic Artificial Intelligencecited by 63
  6. 2020Learning Reasoning Strategies in End-to-End Differentiable Provingcited by 60
  7. 2020Generative Neurosymbolic Machinescited by 57
  8. 2019Embedding Symbolic Knowledge into Deep Networkscited by 49
  9. 2020Turning 30: New Ideas in Inductive Logic Programmingcited by 42
  10. 2020Differentiable Reasoning over a Virtual Knowledge Basecited by 39
  11. 2019NLProlog: Reasoning with Weak Unification for Question Answering in Natural Languagecited by 36
  12. 2016Programming with a Differentiable Forth Interpretercited by 33
  13. 2020Scalable Neural Methods for Reasoning With a Symbolic Knowledge Basecited by 32
  14. 2021EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use casecited by 30
  15. 2016Learning Continuous Semantic Representations of Symbolic Expressionscited by 25
  16. 2019Inductive Logic Programming via Differentiable Deep Neural Logic Networkscited by 25
  17. 2019Logical reduction of metarulescited by 19
  18. 2020Relational Neural Machinescited by 19
  19. 2018On Cognitive Preferences and the Plausibility of Rule-based Modelscited by 14
  20. 2020Beneficial and Harmful Explanatory Machine Learningcited by 13
  21. 2019Learning higher-order logic programscited by 11
  22. 2013Structure Learning of Probabilistic Logic Programs by Searching the Clause Spacecited by 10
  23. 2013Relational Bayesian Networkscited by 7
  24. 2013Programming with Personalized PageRank: A Locally Groundable First-Order Probabilistic Logiccited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 1; 2026: 3.

7 papers.

  1. 2023Neurosymbolic AI for Reasoning over Knowledge Graphs: A Surveycited by 21
  2. 2023Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approachcited by 7
  3. 2023On the Multiple Roles of Ontologies in Explainable AIcited by 2
  4. 2025Predicate Renaming via Large Language Modelscited by 2
  5. 2026AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agentscited by 0
  6. 2026Explaining Reinforcement Learning Agents via Inductive Logic Programmingcited by 0
  7. 2026HyDI: A hybrid Deep Learning-Inductive Logic Programming ensemble for multi-label classificationcited by 0