mlsanityData to 14 Oct 2026

One-shot Machine Teaching: Cost Very Few Examples to Converge Faster

arXiv 2212.06416 ↗First posted 13 Dec 2022cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence is to teach machines to take actions like humans. To achieve intelligent teaching, the machine learning community becomes to think about a promising topic named machine teaching where the teacher is to design the optimal (usually minimal) teaching set given a target model and a specific learner. However, previous works usually require numerous teaching examples along with large iterations to guide learners to converge, which is costly. In this paper, we consider a more intelligent teaching paradigm named one-shot machine teaching which costs fewer examples to converge faster. Different from typical teaching, this advanced paradigm establishes a tractable mapping from the teaching set to the model parameter. Theoretically, we prove that this mapping is surjective, which serves to an existence guarantee of the optimal teaching set. Then, relying on the surjective mapping from the teaching set to the parameter, we develop a design strategy of the optimal teaching set under appropriate settings, of which two popular efficiency metrics, teaching dimension and iterative teaching dimension are one. Extensive experiments verify the efficiency of our strategy and further demonstrate the intelligence of this new teaching paradigm.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 95 references that are in the map. First posted on arXiv 13 Dec 2022.

Builds on

29 of 95 references.

References · 29

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2017One-Shot Imitation Learningcited by 233
  5. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  6. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  7. 2018An Overview of Machine Teachingcited by 63
  8. 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
  9. 2016One-Shot Generalization in Deep Generative Modelscited by 45
  10. 2017Iterative Machine Teachingcited by 41
  11. 2014Near-Optimally Teaching the Crowd to Classifycited by 32
  12. 2019Interactive Teaching Algorithms for Inverse Reinforcement Learningcited by 24
17 more
  1. 2017Towards Black-box Iterative Machine Teachingcited by 20
  2. 2015The Teaching Dimension of Linear Learnerscited by 19
  3. 2013Machine Teaching for Bayesian Learners in the Exponential Familycited by 18
  4. 2018Teaching Multiple Concepts to a Forgetful Learnercited by 17
  5. 2017Human Interaction with Recommendation Systemscited by 15
  6. 2020Commonsense Visual Sensemaking for Autonomous Driving: On Generalised Neurosymbolic Online Abduction Integrating Vision and Semanticscited by 15
  7. 2015Becoming the Expert - Interactive Multi-Class Machine Teachingcited by 12
  8. 2019A Mobile Manipulation System for One-Shot Teaching of Complex Tasks in Homescited by 12
  9. 2018Machine Speech Chain with One-shot Speaker Adaptationcited by 11
  10. 2018An Optimal Control Approach to Sequential Machine Teachingcited by 11
  11. 2021Iterative Teaching by Label Synthesiscited by 10
  12. 2018Iterative Classroom Teachingcited by 8
  13. 2020Iterative Data Programming for Expanding Text Classification Corporacited by 4
  14. 2019Robust Federated Training via Collaborative Machine Teaching using Trusted Instancescited by 3
  15. 2020Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learnerscited by 3
  16. 2016Analysis of a Design Pattern for Teaching with Features and Labelscited by 1
  17. 2020Intuitiveness in Active Teachingcited by 1

Built on by

Not cited yet.