mlsanityData to 7 Oct 2026

Incorporating Domain Knowledge into Deep Neural Networks

arXiv 2103.00180 ↗First posted 27 Feb 2021cs.NE cs.AI cs.LGcited by 56

Not on the map. Why?

Abstract (arXiv)

We present a survey of ways in which domain-knowledge has been included when constructing models with neural networks. The inclusion of domain-knowledge is of special interest not just to constructing scientific assistants, but also, many other areas that involve understanding data using human-machine collaboration. In many such instances, machine-based model construction may benefit significantly from being provided with human-knowledge of the domain encoded in a sufficiently precise form. This paper examines two broad approaches to encode such knowledge--as logical and numerical constraints--and describes techniques and results obtained in several sub-categories under each of these approaches.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 45 of its 142 references that are in the map. First posted on arXiv 27 Feb 2021.

Builds on

45 of 142 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  7. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  8. 2014How transferable are features in deep neural networks?cited by 1,216
  9. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  10. 2016The Mythos of Model Interpretabilitycited by 716
  11. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  12. 2020Knowledge Graphscited by 619
33 more
  1. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  2. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  3. 2017Learning Explanatory Rules from Noisy Datacited by 210
  4. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
  5. 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 203
  6. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 195
  7. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 159
  8. 2020Neural Unsupervised Domain Adaptation in NLP---A Surveycited by 142
  9. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  10. 2020KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQAcited by 124
  11. 2019Knowledge Graph Convolutional Networks for Recommender Systemscited by 121
  12. 2018Embedding Logical Queries on Knowledge Graphscited by 120
  13. 2020Logical Neural Networkscited by 118
  14. 2019Towards Knowledge-Based Recommender Dialog Systemcited by 112
  15. 2019Artificial Intelligence: the global landscape of ethics guidelinescited by 107
  16. 2017Regularization for Deep Learning: A Taxonomycited by 91
  17. 2020From Statistical Relational to Neuro-Symbolic Artificial Intelligencecited by 63
  18. 2019Augmenting Neural Networks with First-order Logiccited by 51
  19. 2019Embedding Symbolic Knowledge into Deep Networkscited by 49
  20. 2019Estimating Node Importance in Knowledge Graphs Using Graph Neural Networkscited by 43
  21. 2020Turning 30: New Ideas in Inductive Logic Programmingcited by 42
  22. 2018Improving the Interpretability of Deep Neural Networks with Knowledge Distillationcited by 37
  23. 2020Semantics of the Black-Box: Can knowledge graphs help make deep learning systems more interpretable and explainable?cited by 31
  24. 2016Lifted Rule Injection for Relation Embeddingscited by 22
  25. 2019Knowledge Infused Learning (K-IL): Towards Deep Incorporation of Knowledge in Deep Learningcited by 19
  26. 2020Incorporating Symbolic Domain Knowledge into Graph Neural Networkscited by 13
  27. 2020Knowledge Graphs and Knowledge Networks: The Story in Briefcited by 11
  28. 2018Logical Explanations for Deep Relational Machines Using Relevance Informationcited by 9
  29. 2020Beyond Graph Neural Networks with Lifted Relational Neural Networkscited by 9
  30. 2020Propositionalization and Embeddings: Two Sides of the Same Coincited by 8
  31. 2020"When they say weed causes depression, but it's your fav antidepressant": Knowledge-aware Attention Framework for Relationship Extractioncited by 8
  32. 2020Injecting Domain Knowledge in Neural Networks: a Controlled Experiment on a Constrained Problemcited by 7
  33. 2018Knowledge-Based Distant Regularization in Learning Probabilistic Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 12; 2023: 8; 2024: 16; 2025: 12; 2026: 6.

56 papers.

Sort:

By area:

  1. 2022Semantic Probabilistic Layers for Neuro-Symbolic Learningcited by 103
  2. 2022A Survey on Graph Representation Learning Methodscited by 66
  3. 2023Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcutscited by 63
  4. 2023Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learningcited by 50
  5. 2022Deep Learning with Logical Constraintscited by 44
  6. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 36
  7. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  8. 2024On the Challenges and Opportunities in Generative AIcited by 31
  9. 2024LAMBDA: A Large Model Based Data Agentcited by 30
  10. 2024A Survey on Large Language Model-based Agents for Statistics and Data Sciencecited by 22
  11. 2022EINNs: Epidemiologically-informed Neural Networkscited by 21
  12. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
38 more
  1. 2024Vehicle: Bridging the Embedding Gap in the Verification of Neuro-Symbolic Programscited by 14
  2. 2024Geometry-Informed Neural Networkscited by 12
  3. 2023GLUECons: A Generic Benchmark for Learning Under Constraintscited by 9
  4. 2024Using Large Language Models to Compare Explainable Models for Smart Home Human Activity Recognitioncited by 9
  5. 2022Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Taskcited by 8
  6. 2024Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learnerscited by 8
  7. 2021AI Descartes: Combining Data and Theory for Derivable Scientific Discoverycited by 7
  8. 2022Neuro-Symbolic Learning: Principles and Applications in Ophthalmologycited by 7
  9. 2023Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspacecited by 7
  10. 2022Wide-Area Geolocalization with a Limited Field of View Cameracited by 5
  11. 2024Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systemscited by 5
  12. 2025A Language Anchor-Guided Method for Robust Noisy Domain Generalizationcited by 5
  13. 2025Domain-Enhanced Dual-Branch Model for Efficient and Interpretable Accident Anticipationcited by 5
  14. 2023Planning with Logical Graph-based Language Model for Instruction Generationcited by 4
  15. 2024Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningcited by 4
  16. 2025Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Huntingcited by 4
  17. 2025Towards Responsible and Trustworthy Educational Data Mining: Comparing Symbolic, Sub-Symbolic, and Neural-Symbolic AI Methodscited by 3
  18. 2025Towards responsible AI for education: Hybrid human-AI to confront the Elephant in the roomcited by 3
  19. 2025ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Searchcited by 3
  20. 2025Physics-Informed Spectral Modeling for Hyperspectral Imagingcited by 2
  21. 2022Movement Analytics: Current Status, Application to Manufacturing, and Future Prospects from an AI Perspectivecited by 1
  22. 2022Brain informed transfer learning for categorizing construction hazardscited by 1
  23. 2022Phases, Modalities, Temporal and Spatial Locality: Domain Specific ML Prefetcher for Accelerating Graph Analyticscited by 1
  24. 2023DKINet: Medication Recommendation via Domain Knowledge Informed Deep Learningcited by 1
  25. 2023Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniquescited by 1
  26. 2024Auxiliary Input in Training: Incorporating Catheter Features into Deep Learning Models for ECG-Free Dynamic Coronary Roadmappingcited by 1
  27. 2025Domain Consistent Industrial Decarbonisation of Global Coal Power Plantscited by 1
  28. 2025Informed Learning for Estimating Drought Stress at Fine-Scale Resolution Enables Accurate Yield Predictioncited by 1
  29. 2026Knowledge, Rules and Their Embeddings: Two Paths towards Neuro-Symbolic JEPAcited by 1
  30. 2021Superpixel-based Knowledge Infusion in Deep Neural Networks for Image Classificationcited by 0
  31. 2022Neural Feature-Adaptation for Symbolic Predictions Using Pre-Training and Semantic Losscited by 0
  32. 2023VALUED -- Vision and Logical Understanding Evaluation Datasetcited by 0
  33. 2024Image classification network enhancement methods based on knowledge injectioncited by 0
  34. 2024Deep Neural Network for Constraint Acquisition through Tailored Loss Functioncited by 0
  35. 2024ContextGPT: Infusing LLMs Knowledge into Neuro-Symbolic Activity Recognition Modelscited by 0
  36. 2024Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddingscited by 0
  37. 2025Addressing Quality Challenges in Deep Learning: The Role of MLOps and Domain Knowledgecited by 0
  38. 2025Small Data Explainer -- The impact of small data methods in everyday lifecited by 0

50 most cited of 56 All 56 (JSON)