# Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases

arXiv: https://arxiv.org/abs/2102.11965 · HTML: https://mlsanity.com/paper/2102.11965/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 75 references that are in the map.
- First posted on arXiv 23 Feb 2021.

## Builds on (most cited first, 30 of 32)

- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [A Semantic Loss Function for Deep Learning with Symbolic Knowledge](https://mlsanity.com/paper/1711.11157/) (2017)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Representation Tradeoffs for Hyperbolic Embeddings](https://mlsanity.com/paper/1804.03329/) (2018)
- [End-to-End Differentiable Proving](https://mlsanity.com/paper/1705.11040/) (2017)
- [Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning](https://mlsanity.com/paper/1905.06088/) (2019)
- [Logic Tensor Networks for Semantic Image Interpretation](https://mlsanity.com/paper/1705.08968/) (2017)
- [Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution](https://mlsanity.com/paper/1801.04016/) (2018)
- [Hinge-Loss Markov Random Fields and Probabilistic Soft Logic](https://mlsanity.com/paper/1505.04406/) (2015)
- [Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning](https://mlsanity.com/paper/1903.08948/) (2019)
- [From Statistical Relational to Neuro-Symbolic Artificial Intelligence](https://mlsanity.com/paper/2003.08316/) (2020)
- [Graph Kernels: State-of-the-Art and Future Challenges](https://mlsanity.com/paper/2011.03854/) (2020)
- [Deep Network Guided Proof Search](https://mlsanity.com/paper/1701.06972/) (2017)
- [Towards Deep Symbolic Reinforcement Learning](https://mlsanity.com/paper/1609.05518/) (2016)
- [Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base](https://mlsanity.com/paper/2002.06115/) (2020)
- [Efficient Generation of Structured Objects with Constrained Adversarial Networks](https://mlsanity.com/paper/2007.13197/) (2020)
- [Unsupervised Grounding of Plannable First-Order Logic Representation from Images](https://mlsanity.com/paper/1902.08093/) (2019)
- [Lifted Rule Injection for Relation Embeddings](https://mlsanity.com/paper/1606.08359/) (2016)
- [A Boxology of Design Patterns for Hybrid Learning and Reasoning Systems](https://mlsanity.com/paper/1905.12389/) (2019)
- [Relational Neural Machines](https://mlsanity.com/paper/2002.02193/) (2020)
- [Teaching the Old Dog New Tricks: Supervised Learning with Constraints](https://mlsanity.com/paper/2002.10766/) (2020)
- [Accuracy-based Curriculum Learning in Deep Reinforcement Learning](https://mlsanity.com/paper/1806.09614/) (2018)
- [Explaining Trained Neural Networks with Semantic Web Technologies: First Steps](https://mlsanity.com/paper/1710.04324/) (2017)
- [Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions](https://mlsanity.com/paper/1809.00204/) (2018)
- [Human-Level Intelligence or Animal-Like Abilities?](https://mlsanity.com/paper/1707.04327/) (2017)
- [Injecting Domain Knowledge in Neural Networks: a Controlled Experiment on a Constrained Problem](https://mlsanity.com/paper/2002.10742/) (2020)
- [Reasoning over RDF Knowledge Bases using Deep Learning](https://mlsanity.com/paper/1811.04132/) (2018)

## Built on by (most cited first, 30 of 39)

- [From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey](https://mlsanity.com/paper/2108.11451/) (2021)
- [Meaningful human control: actionable properties for AI system development](https://mlsanity.com/paper/2112.01298/) (2021)
- [Human-AI collaboration is not very collaborative yet: A taxonomy of interaction patterns in AI-assisted decision making from a systematic review](https://mlsanity.com/paper/2310.19778/) (2023)
- [Ontology Embedding: A Survey of Methods, Applications and Resources](https://mlsanity.com/paper/2406.10964/) (2024)
- [Knowledge Engineering using Large Language Models](https://mlsanity.com/paper/2310.00637/) (2023)
- [Defining neurosymbolic AI](https://mlsanity.com/paper/2507.11127/) (2025)
- [Unpacking Human-AI interactions: From interaction primitives to a design space](https://mlsanity.com/paper/2401.05115/) (2024)
- [Natlog: a Lightweight Logic Programming Language with a Neuro-symbolic Touch](https://mlsanity.com/paper/2109.08291/) (2021)
- [Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarios](https://mlsanity.com/paper/2211.05455/) (2022)
- [Describing and Organizing Semantic Web and Machine Learning Systems in the SWeMLS-KG](https://mlsanity.com/paper/2303.15113/) (2023)
- [The DeepLog Neurosymbolic Machine](https://mlsanity.com/paper/2508.13697/) (2025)
- [Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories](https://mlsanity.com/paper/2308.10562/) (2023)
- [PROTOtypical Logic Tensor Networks (PROTO-LTN) for Zero Shot Learning](https://mlsanity.com/paper/2207.00433/) (2022)
- [Combining Machine Learning and Ontology: A Systematic Literature Review](https://mlsanity.com/paper/2401.07744/) (2024)
- [Modular Design Patterns for Hybrid Actors](https://mlsanity.com/paper/2109.09331/) (2021)
- [Ontology Pre-training for Poison Prediction](https://mlsanity.com/paper/2301.08577/) (2023)
- [Trust, Accountability, and Autonomy in Knowledge Graph-based AI for Self-determination](https://mlsanity.com/paper/2310.19503/) (2023)
- [Aligning Generalisation Between Humans and Machines](https://mlsanity.com/paper/2411.15626/) (2024)
- [Knowledge Affordances for Hybrid Human-AI Information Seeking](https://mlsanity.com/paper/2604.27539/) (2026)
- [Modular design patterns for neural-symbolic integration: refinement and combination](https://mlsanity.com/paper/2206.04724/) (2022)
- [Ontology in Hybrid Intelligence: a concise literature review](https://mlsanity.com/paper/2303.17262/) (2023)
- [Fuzzy Logic Visual Network (FLVN): A neuro-symbolic approach for visual features matching](https://mlsanity.com/paper/2307.16019/) (2023)
- [Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification](https://mlsanity.com/paper/2402.19339/) (2024)
- [IID Relaxation by Logical Expressivity: A Research Agenda for Fitting Logics to Neurosymbolic Requirements](https://mlsanity.com/paper/2404.19485/) (2024)
- [Mutual Understanding between People and Systems via Neurosymbolic AI and Knowledge Graphs](https://mlsanity.com/paper/2504.11200/) (2025)
- [DeepGraphLog for Layered Neurosymbolic AI](https://mlsanity.com/paper/2509.07665/) (2025)
- [Discovering Association Rules in High-Dimensional Small Tabular Data](https://mlsanity.com/paper/2509.20113/) (2025)
- [Neuro-symbolic Action Masking for Deep Reinforcement Learning](https://mlsanity.com/paper/2602.10598/) (2026)
- [The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning](https://mlsanity.com/paper/2608.04285/) (2026)
- [Natural Computational Architectures for Cognitive Info-Communication](https://mlsanity.com/paper/2110.06339/) (2021)

## Abstract (arXiv)

The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognised as one of the key challenges of modern AI. Recent years have seen large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse and mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper we analyse a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks. The main contributions of this paper are: 1) a taxonomically organised vocabulary to describe both processes and data structures used in hybrid systems; 2) a set of 15+ design patterns for hybrid AI systems, organised in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems. Our patterns reveal similarities between systems that were not recognised until now. Finally, our design patterns extend and refine Kautz' earlier attempt at categorising neuro-symbolic architectures.