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

arXiv: https://arxiv.org/abs/2212.06416 · HTML: https://mlsanity.com/paper/2212.06416/

## 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 (most cited first, 29 of 29)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [Delta-encoder: an effective sample synthesis method for few-shot object recognition](https://mlsanity.com/paper/1806.04734/) (2018)
- [An Overview of Machine Teaching](https://mlsanity.com/paper/1801.05927/) (2018)
- [Multi-level Semantic Feature Augmentation for One-shot Learning](https://mlsanity.com/paper/1804.05298/) (2018)
- [One-Shot Generalization in Deep Generative Models](https://mlsanity.com/paper/1603.05106/) (2016)
- [Iterative Machine Teaching](https://mlsanity.com/paper/1705.10470/) (2017)
- [Near-Optimally Teaching the Crowd to Classify](https://mlsanity.com/paper/1402.2092/) (2014)
- [Interactive Teaching Algorithms for Inverse Reinforcement Learning](https://mlsanity.com/paper/1905.11867/) (2019)
- [Towards Black-box Iterative Machine Teaching](https://mlsanity.com/paper/1710.07742/) (2017)
- [The Teaching Dimension of Linear Learners](https://mlsanity.com/paper/1512.02181/) (2015)
- [Machine Teaching for Bayesian Learners in the Exponential Family](https://mlsanity.com/paper/1306.4947/) (2013)
- [Teaching Multiple Concepts to a Forgetful Learner](https://mlsanity.com/paper/1805.08322/) (2018)
- [Human Interaction with Recommendation Systems](https://mlsanity.com/paper/1703.00535/) (2017)
- [Commonsense Visual Sensemaking for Autonomous Driving: On Generalised Neurosymbolic Online Abduction Integrating Vision and Semantics](https://mlsanity.com/paper/2012.14359/) (2020)
- [Becoming the Expert - Interactive Multi-Class Machine Teaching](https://mlsanity.com/paper/1504.07575/) (2015)
- [A Mobile Manipulation System for One-Shot Teaching of Complex Tasks in Homes](https://mlsanity.com/paper/1910.00127/) (2019)
- [Machine Speech Chain with One-shot Speaker Adaptation](https://mlsanity.com/paper/1803.10525/) (2018)
- [An Optimal Control Approach to Sequential Machine Teaching](https://mlsanity.com/paper/1810.06175/) (2018)
- [Iterative Teaching by Label Synthesis](https://mlsanity.com/paper/2110.14432/) (2021)
- [Iterative Classroom Teaching](https://mlsanity.com/paper/1811.03537/) (2018)
- [Iterative Data Programming for Expanding Text Classification Corpora](https://mlsanity.com/paper/2002.01412/) (2020)
- [Robust Federated Training via Collaborative Machine Teaching using Trusted Instances](https://mlsanity.com/paper/1905.02941/) (2019)
- [Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners](https://mlsanity.com/paper/2009.02476/) (2020)
- [Analysis of a Design Pattern for Teaching with Features and Labels](https://mlsanity.com/paper/1611.05950/) (2016)
- [Intuitiveness in Active Teaching](https://mlsanity.com/paper/2012.13551/) (2020)

## 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.