mlsanityData to 7 Oct 2026

Harnessing Deep Neural Networks with Logic Rules

arXiv 1603.06318 ↗First posted 21 Mar 2016cs.LG cs.AI cs.CLcited by 135

Not on the map. Why?

Abstract (arXiv)

Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules. Specifically, we develop an iterative distillation method that transfers the structured information of logic rules into the weights of neural networks. We deploy the framework on a CNN for sentiment analysis, and an RNN for named entity recognition. With a few highly intuitive rules, we obtain substantial improvements and achieve state-of-the-art or comparable results to previous best-performing systems.

Key facts. Cited by 135 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 46; 2022: 23; 2023: 38; 2024: 16; 2025: 6; 2026: 6.

135 papers.

Sort:

By area:

  1. 2021A Survey on Deep Semi-supervised Learningcited by 250
  2. 2021Does Knowledge Distillation Really Work?cited by 187
  3. 2021Towards Understanding Knowledge Distillationcited by 158
  4. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  5. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  6. 2021Adaptive Multi-Teacher Multi-level Knowledge Distillationcited by 69
  7. 2021Incorporating Domain Knowledge into Deep Neural Networkscited by 56
  8. 2021Automated Fact-Checking: A Surveycited by 55
  9. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  10. 2021Self-Training with Weak Supervisioncited by 49
  11. 2021MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networkscited by 44
  12. 2022Deep Learning with Logical Constraintscited by 44
38 more
  1. 2021A Survey on Neural-symbolic Learning Systemscited by 39
  2. 2021Multi-Label Classification Neural Networks with Hard Logical Constraintscited by 36
  3. 2021A Systematic Review of Reproducibility Research in Natural Language Processingcited by 34
  4. 2022NeuPSL: Neural Probabilistic Soft Logiccited by 34
  5. 2022ROAD-R: The Autonomous Driving Dataset with Logical Requirementscited by 34
  6. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  7. 2021EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use casecited by 30
  8. 2021Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approachescited by 30
  9. 2023TABLET: Learning From Instructions For Tabular Datacited by 28
  10. 2022Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignmentcited by 27
  11. 2023Neural-Logic Human-Object Interaction Detectioncited by 25
  12. 2022BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Modelscited by 20
  13. 2021Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possiblecited by 19
  14. 2021Churn Reduction via Distillationcited by 17
  15. 2022Utilizing Expert Features for Contrastive Learning of Time-Series Representationscited by 17
  16. 2023RECKONING: Reasoning through Dynamic Knowledge Encodingcited by 17
  17. 2023LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoningcited by 17
  18. 2021Controlling Neural Networks with Rule Representationscited by 16
  19. 2021Neuro-Symbolic Forward Reasoningcited by 16
  20. 2023Interpretable Multimodal Misinformation Detection with Logic Reasoningcited by 16
  21. 2023Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Modelscited by 16
  22. 2024Softened Symbol Grounding for Neuro-symbolic Systemscited by 16
  23. 2021Learning Logic Rules for Document-level Relation Extractioncited by 15
  24. 2023Logic of Differentiable Logics: Towards a Uniform Semantics of DLcited by 15
  25. 2024SymbolicAI: A framework for logic-based approaches combining generative models and solverscited by 15
  26. 2022PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learningcited by 14
  27. 2023More than Classification: A Unified Framework for Event Temporal Relation Extractioncited by 14
  28. 2023KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repaircited by 13
  29. 2023A Call for Standardization and Validation of Text Style Transfer Evaluationcited by 13
  30. 2023On Learning Latent Models with Multi-Instance Weak Supervisioncited by 13
  31. 2023CuTS: Customizable Tabular Synthetic Data Generationcited by 12
  32. 2021Neuro-Symbolic Constraint Programming for Structured Predictioncited by 11
  33. 2021ACP++: Action Co-occurrence Priors for Human-Object Interaction Detectioncited by 11
  34. 2021Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programmingcited by 11
  35. 2022CARE: Certifiably Robust Learning with Reasoning via Variational Inferencecited by 10
  36. 2023Assessing SATNet's Ability to Solve the Symbol Grounding Problemcited by 10
  37. 2024Learning with Logical Constraints but without Shortcut Satisfactioncited by 10
  38. 2021Recent Trends in Named Entity Recognition (NER)cited by 9

50 most cited of 135 All 135 (JSON)