mlsanityData to 7 Oct 2026

Iterative Teaching by Data Hallucination

arXiv 2210.17467 ↗First posted 31 Oct 2022cs.LG cs.AI cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

We consider the problem of iterative machine teaching, where a teacher sequentially provides examples based on the status of a learner under a discrete input space (i.e., a pool of finite samples), which greatly limits the teacher's capability. To address this issue, we study iterative teaching under a continuous input space where the input example (i.e., image) can be either generated by solving an optimization problem or drawn directly from a continuous distribution. Specifically, we propose data hallucination teaching (DHT) where the teacher can generate input data intelligently based on labels, the learner's status and the target concept. We study a number of challenging teaching setups (e.g., linear/neural learners in omniscient and black-box settings). Extensive empirical results verify the effectiveness of DHT.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 60 of its 86 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

60 of 86 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  9. 2013Auto-Encoding Variational Bayescited by 3,980
  10. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  11. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  12. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
38 more
  1. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  2. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  3. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  4. 2016Learning to learn by gradient descent by gradient descentcited by 616
  5. 2020Dataset Condensation with Gradient Matchingcited by 510
  6. 2017Progressive Neural Architecture Searchcited by 483
  7. 2022Dataset Distillation by Matching Training Trajectoriescited by 437
  8. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  9. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 333
  10. 2020Performative Predictioncited by 318
  11. 2018Dataset Distillationcited by 224
  12. 2019Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Ratescited by 119
  13. 2018A Kernel Theory of Modern Data Augmentationcited by 106
  14. 2020Adaptive Reward-Poisoning Attacks against Reinforcement Learningcited by 86
  15. 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
  16. 2018Learning towards Minimum Hyperspherical Energycited by 75
  17. 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
  18. 2018Bayesian Coreset Construction via Greedy Iterative Geodesic Ascentcited by 68
  19. 2018An Overview of Machine Teachingcited by 63
  20. 2018Decoupled Networkscited by 45
  21. 2020Orthogonal Over-Parameterized Trainingcited by 44
  22. 2022Performative Powercited by 42
  23. 2017Iterative Machine Teachingcited by 40
  24. 2014Near-Optimally Teaching the Crowd to Classifycited by 32
  25. 2018Teaching Categories to Human Learners with Visual Explanationscited by 30
  26. 2019Angular Visual Hardnesscited by 29
  27. 2018Training Set Debugging Using Trusted Itemscited by 24
  28. 2019Interactive Teaching Algorithms for Inverse Reinforcement Learningcited by 24
  29. 2019A mathematical theory of cooperative communicationcited by 23
  30. 2015The Teaching Dimension of Linear Learnerscited by 19
  31. 2017Towards Black-box Iterative Machine Teachingcited by 19
  32. 2018Teaching Inverse Reinforcement Learners via Features and Demonstrationscited by 19
  33. 2013Machine Teaching for Bayesian Learners in the Exponential Familycited by 18
  34. 2019Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraintscited by 18
  35. 2018Teaching Multiple Concepts to a Forgetful Learnercited by 17
  36. 2018Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learnerscited by 16
  37. 2013Are all training examples equally valuable?cited by 14
  38. 2015Becoming the Expert - Interactive Multi-Class Machine Teachingcited by 12

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 2; 2025: 1.

8 papers.

  1. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
  2. 2023Nonparametric Iterative Machine Teachingcited by 9
  3. 2022Human-in-the-Loop Mixupcited by 8
  4. 2023Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillationcited by 8
  5. 2023Nonparametric Teaching for Multiple Learnerscited by 7
  6. 2025Model Merging with Functional Dual Anchorscited by 4
  7. 2024Representational Alignment Supports Effective Machine Teachingcited by 3
  8. 2024L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancementcited by 2