mlsanityData to 14 Oct 2026

Knowledge-augmented Deep Learning and Its Applications: A Survey

arXiv 2212.00017 ↗First posted 30 Nov 2022cs.LG cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Deep learning models, though having achieved great success in many different fields over the past years, are usually data hungry, fail to perform well on unseen samples, and lack of interpretability. Various prior knowledge often exists in the target domain and their use can alleviate the deficiencies with deep learning. To better mimic the behavior of human brains, different advanced methods have been proposed to identify domain knowledge and integrate it into deep models for data-efficient, generalizable, and interpretable deep learning, which we refer to as knowledge-augmented deep learning (KADL). In this survey, we define the concept of KADL, and introduce its three major tasks, i.e., knowledge identification, knowledge representation, and knowledge integration. Different from existing surveys that are focused on a specific type of knowledge, we provide a broad and complete taxonomy of domain knowledge and its representations. Based on our taxonomy, we provide a systematic review of existing techniques, different from existing works that survey integration approaches agnostic to taxonomy of knowledge. This survey subsumes existing works and offers a bird's-eye view of research in the general area of knowledge-augmented deep learning. The thorough and critical reviews of numerous papers help not only understand current progresses but also identify future directions for the research on knowledge-augmented deep learning.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 78 of its 152 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

78 of 152 references.

References · 78

  1. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  2. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  3. 2019Hamiltonian Neural Networkscited by 712
  4. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  5. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 509
  6. 2020Lagrangian Neural Networkscited by 398
  7. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 270
  8. 2019Cormorant: Covariant Molecular Neural Networkscited by 263
  9. 2019Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Datacited by 262
  10. 2018Deep Learning: A Critical Appraisalcited by 217
  11. 2017Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanicscited by 214
  12. 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 212
38 more
  1. 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 205
  2. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 196
  3. 2019Symplectic ODE-Net: Learning Hamiltonian Dynamics with Controlcited by 184
  4. 2022Modeling Indirect Illumination for Inverse Renderingcited by 168
  5. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 145
  6. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 144
  7. 2019TossingBot: Learning to Throw Arbitrary Objects with Residual Physicscited by 137
  8. 2019Hamiltonian Generative Networkscited by 137
  9. 2019Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networkscited by 129
  10. 2020Incorporating Symmetry into Deep Dynamics Models for Improved Generalizationcited by 126
  11. 2020KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQAcited by 125
  12. 2018Adversarial Uncertainty Quantification in Physics-Informed Neural Networkscited by 120
  13. 2016A Compositional Object-Based Approach to Learning Physical Dynamicscited by 119
  14. 2020Logical Neural Networkscited by 119
  15. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 114
  16. 2021Energy-Based Learning for Scene Graph Generationcited by 104
  17. 2019Scene Graph Generation with External Knowledge and Image Reconstructioncited by 102
  18. 2020Augmenting Physical Models with Deep Networks for Complex Dynamics Forecastingcited by 95
  19. 2019Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discoverycited by 93
  20. 2017Logic Tensor Networks for Semantic Image Interpretationcited by 92
  21. 2021Residual Pathway Priors for Soft Equivariance Constraintscited by 75
  22. 2016Label-Free Supervision of Neural Networks with Physics and Domain Knowledgecited by 74
  23. 2021Neural Monocular 3D Human Motion Capture with Physical Awarenesscited by 71
  24. 2019Probabilistic Logic Neural Networks for Reasoningcited by 69
  25. 2021SE(3)-equivariant prediction of molecular wavefunctions and electronic densitiescited by 67
  26. 2017Visual Relationship Detection with Internal and External Linguistic Knowledge Distillationcited by 61
  27. 2020Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profilescited by 59
  28. 2021Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modelingcited by 59
  29. 2018Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profilescited by 55
  30. 2020Deep Imitation Learning for Bimanual Robotic Manipulationcited by 50
  31. 2019Embedding Symbolic Knowledge into Deep Networkscited by 49
  32. 2019Estimating 3D Motion and Forces of Person-Object Interactions from Monocular Videocited by 48
  33. 2021Zero-Shot Day-Night Domain Adaptation with a Physics Priorcited by 47
  34. 2021Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generationcited by 47
  35. 2021Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modelingcited by 41
  36. 2020Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effectscited by 40
  37. 2022Differentiable Simulation of Soft Multi-body Systemscited by 39
  38. 2018Deep Structure Inference Network for Facial Action Unit Recognitioncited by 38

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 3; 2026: 1.

10 papers.

  1. 2023Chain of Thought Prompting Elicits Knowledge Augmentationcited by 21
  2. 2023Knowledge-augmented Graph Machine Learning for Drug Discovery: A Surveycited by 6
  3. 2023Knowledge-enhanced Neural Machine Reasoning: A Reviewcited by 3
  4. 2025Diffusion Secant Alignment for Score-Based Density Ratio Estimationcited by 3
  5. 2023The Expert Knowledge combined with AI outperforms AI Alone in Seizure Onset Zone Localization using resting state fMRIcited by 2
  6. 2024Quantitative Analysis of Molecular Transport in the Extracellular Space Using Physics-Informed Neural Networkcited by 0
  7. 2024SPIN: SE(3)-Invariant Physics Informed Network for Binding Affinity Predictioncited by 0
  8. 2025Task-Agnostic Federation over Decentralized Data: Research Landscape and Visionscited by 0
  9. 2025FRAME-C: A knowledge-augmented deep learning pipeline for classifying multi-electrode array electrophysiological signalscited by 0
  10. 2026Revisiting Euler-Angle Regression with Kolmogorov-Arnold Networkscited by 0