mlsanityData to 7 Oct 2026

A Boxology of Design Patterns for Hybrid Learning and Reasoning Systems

arXiv 1905.12389 ↗First posted 29 May 2019cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

We propose a set of compositional design patterns to describe a large variety of systems that combine statistical techniques from machine learning with symbolic techniques from knowledge representation. As in other areas of computer science (knowledge engineering, software engineering, ontology engineering, process mining and others), such design patterns help to systematize the literature, clarify which combinations of techniques serve which purposes, and encourage re-use of software components. We have validated our set of compositional design patterns against a large body of recent literature.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 5; 2023: 3; 2024: 2; 2025: 4; 2026: 2.

20 papers.

Sort:

By area:

  1. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  2. 2022A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inferencecited by 50
  3. 2021Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use casescited by 39
  4. 2022Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Reviewcited by 37
  5. 2025Neurosymbolic Diffusion Modelscited by 12
  6. 2023Knowledge Engineering using Large Language Modelscited by 9
  7. 2024ULLER: A Unified Language for Learning and Reasoningcited by 9
  8. 2025Defining neurosymbolic AIcited by 7
  9. 2023Describing and Organizing Semantic Web and Machine Learning Systems in the SWeMLS-KGcited by 5
  10. 2025The DeepLog Neurosymbolic Machinecited by 3
  11. 2021Modular Design Patterns for Hybrid Actorscited by 2
  12. 2022Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methodscited by 2
8 more
  1. 2026Knowledge Affordances for Hybrid Human-AI Information Seekingcited by 2
  2. 2022Differentiable Fuzzy ALC: A Neural-Symbolic Representation Language for Symbol Groundingcited by 1
  3. 2023Teach Me How to Learn: A Perspective Review towards User-centered Neuro-symbolic Learning for Robotic Surgical Systemscited by 1
  4. 2025Mutual Understanding between People and Systems via Neurosymbolic AI and Knowledge Graphscited by 1
  5. 2021Moral Decision-Making in Medical Hybrid Intelligent Systems: A Team Design Patterns Approach to the Bias Mitigation and Data Sharing Design Problemscited by 0
  6. 2022Commonsense Reasoning for Identifying and Understanding the Implicit Need of Help and Synthesizing Assistive Actionscited by 0
  7. 2024Standardizing Knowledge Engineering Practices with a Reference Architecturecited by 0
  8. 2026Ontology-Mediated Neurosymbolic Constraint Acquisition from Multiple Stakeholderscited by 0