mlsanityData to 14 Oct 2026

A Learnability Analysis on Neuro-Symbolic Learning

arXiv 2503.16797 ↗First posted 21 Mar 2025cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper analyzes the learnability of neuro-symbolic (NeSy) tasks within hybrid systems. We show that the learnability of NeSy tasks can be characterized by their derived constraint satisfaction problems (DCSPs). Specifically, a task is learnable if the corresponding DCSP has a unique solution; otherwise, it is unlearnable. For learnable tasks, we establish error bounds by exploiting the clustering property of the hypothesis space. Additionally, we analyze the asymptotic error for general NeSy tasks, showing that the expected error scales with the disagreement among solutions. Our results offer a principled approach to determining learnability and provide insights into the design of new algorithms.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 28 of its 71 references that are in the map. First posted on arXiv 21 Mar 2025.

Builds on

28 of 71 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  4. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  5. 2018Deep Learning for Classical Japanese Literaturecited by 422
  6. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 394
  7. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 372
  8. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 270
  9. 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 205
  10. 2020Logic Tensor Networkscited by 199
  11. 2020Analyzing Differentiable Fuzzy Logic Operatorscited by 101
  12. 2020Explainable Object-induced Action Decision for Autonomous Vehiclescited by 88
16 more
  1. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  2. 2023Scallop: A Language for Neurosymbolic Programmingcited by 63
  3. 2023Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcutscited by 63
  4. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 37
  5. 2023Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsalcited by 33
  6. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
  7. 2023On Learning Latent Models with Multi-Instance Weak Supervisioncited by 13
  8. 2024Neuro-symbolic Learning Yielding Logical Constraintscited by 12
  9. 2024Learning with Logical Constraints but without Shortcut Satisfactioncited by 10
  10. 2024On the Hardness of Probabilistic Neurosymbolic Learningcited by 9
  11. 2024Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflectioncited by 9
  12. 2025Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Reviewcited by 7
  13. 2023Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guaranteescited by 6
  14. 2024Relational Neurosymbolic Markov Modelscited by 6
  15. 2025Valid Text-to-SQL Generation with Unification-based DeepStochLogcited by 3
  16. 2022Reduced Implication-bias Logic Loss for Neuro-Symbolic Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learningcited by 2
  2. 2025Curriculum Abductive Learningcited by 1
  3. 2026Candidate Retention for Abductive Learningcited by 0