An Overview of Machine Teaching

By Xiaojin Zhu, Adish Kumar Singla, Sandra Zilles, Anna N. Rafferty. 2018

193 citations recorded by the source corpus.

In this paper we try to organize machine teaching as a coherent set of ideas. Each idea is presented as varying along a dimension. The collection of dimensions then form the problem space of machine teaching, such that existing teaching problems can be characterized in this space. We hope this organization allows us to gain deeper understanding of individual teaching problems, discover connections among them, and identify gaps in the field.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning (2020, background): “Machine teaching is closely related to data poisoning [48], and is the process by which one designs training data to drive a learning algorithm to a target model.”
Teaching a black-box learner (2019, background): “The literature on teaching can be organized along two main dimensions: whether the learner is required to be consistent with all teaching examples and whether the teacher has full knowledge of the learner (Zhu et al., 2018).”
Teacher Improves Learning by Selecting a Training Subset (2018, background): “As such, the question is not a machine learning task but rather a machine teaching one [47, 20, 45].”
A Competence-aware Curriculum for Visual Concepts Learning via Question Answering (2020, background): “The competence-aware curriculum in our work is related to curriculum learning [7,54,56,20,51,45,21,48] and machine teaching [61,62,39,11,41,15,58].”
Human-in-the-loop machine learning: a state of the art (2022, background): “Zhu et al. (2018) adds a new dimension here that has to do not only with the number of cases presented to the model but also with their ordering.”
Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications (2018, background): “Like most machine teaching problems (Zhu et al. 2018), the machine teaching problem for IRL is a difﬁcult optimization problem.”
TIP: Typifying the Interpretability of Procedures (2017, background): “Other relevant literatures where information is transfered between two or more entities can be witnessed in multi-agent coordination [8] and machine teaching [55].”
Optimization Models for Machine Learning: A Survey (2019, background): “With the intent to generalize the teaching dimension problem to a variety of teaching tasks, [219] and [220] provide the Machine Teaching framework.”
An Optimal Control Approach to Sequential Machine Teaching (2018, background): “Machine teaching studies optimal control on machine learners (Zhu et al., 2018; Zhu, 2015).”