An Overview of Machine Teaching

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.

• Publication year

  2018

• Venue

  arXiv.org

• Publication date

  2018-01-18

• Fields of study

  Computer Science, Education

• Identifiers
  arXiv 1801.05927
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Approximately Optimal Teaching of Approximately Optimal Learners

  2018cited by this paper
• Training Set Debugging Using Trusted Items

  2018cited by this paper
• Machine Teaching: A New Paradigm for Building Machine Learning Systems

  2017influential reference
• Optimizing Human Learning

  2017cited by this paper
• Iterative Machine Teaching

  2017cited by this paper
• Explicit Defense Actions Against Test-Set Attacks

  2017cited by this paper
• Active Classification with Comparison Queries

  2017cited by this paper
• Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes

  2017cited by this paper
• No Learner Left Behind: On the Complexity of Teaching Multiple Learners Simultaneously

  2017cited by this paper
• Showing versus doing: Teaching by demonstration

  2016cited by this paper
• Preference-based Teaching

  2016cited by this paper
• The Label Complexity of Mixed-Initiative Classifier Training

  2016cited by this paper
• Faster Teaching via POMDP Planning

  2016cited by this paper
• Trusted Machine Learning for Probabilistic Models

  2016cited by this paper
• Data Poisoning Attacks against Autoregressive Models

  2016cited by this paper
• Interactive Learning from Multiple Noisy Labels

  2016cited by this paper
• A Trainable Spaced Repetition Model for Language Learning

  2016cited by this paper
• Debugging Machine Learning Models

  2016cited by this paper
• Open Problem: Recursive Teaching Dimension Versus VC Dimension

  2015influential reference
• The Security of Latent Dirichlet Allocation

  2015cited by this paper
• Using Machine Teaching to Identify Optimal Training-Set Attacks on Machine Learners

  2015cited by this paper
• The Teaching Dimension of Linear Learners

  2015cited by this paper
• Machine Teaching: An Inverse Problem to Machine Learning and an Approach Toward Optimal Education

  2015cited by this paper
• Automatic Discovery of Cognitive Skills to Improve the Prediction of Student Learning

  2014cited by this paper
• Optimal Teaching for Limited-Capacity Human Learners

  2014cited by this paper
• Modeling the dynamics of classroom education using teaching games

  2014cited by this paper
• Recursive teaching dimension, VC-dimension and sample compression

  2014influential reference
• A rational account of pedagogical reasoning: teaching by, and learning from, examples.

  2014cited by this paper
• Near-Optimally Teaching the Crowd to Classify

  2014cited by this paper
• Eliciting good teaching from humans for machine learners

  2014cited by this paper
• Teaching People How to Teach Robots: The Effect of Instructional Materials and Dialog Design

  2014cited by this paper
• Improving Students’ Long-Term Knowledge Retention Through Personalized Review

  2014cited by this paper
• Optimizing Instructional Policies

  2013cited by this paper
• On Actively Teaching the Crowd to Classify

  2013cited by this paper
• Order compression schemes

  2013cited by this paper
• Machine Teaching for Bayesian Learners in the Exponential Family

  2013cited by this paper
• Trajectories and keyframes for kinesthetic teaching: A human-robot interaction perspective

  2012influential reference
• Algorithmic and Human Teaching of Sequential Decision Tasks

  2012cited by this paper
• Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization

  2010cited by this paper
• Curriculum learning

  2009cited by this paper
• Learning about objects with human teachers

  2009influential reference
• Measuring teachability using variants of the teaching dimension

  2008cited by this paper
• Relating Data Compression and Learnability

  2003cited by this paper
• Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping

  1999cited by this paper
• Teaching a Smarter Learner

  1996cited by this paper
• Sample compression, learnability, and the Vapnik-Chervonenkis dimension

  1995cited by this paper
• On the complexity of teaching

  1991cited by this paper
• Robotics and autonomous systems

  1988cited by this paper
• Journal of Machine Learning Research x (2011) xx-xx Submitted 6/10; Revised 12/10; Published x/11 Models of Cooperative Teaching and Learning

  year unknowncited by this paper

• Nonparametric Teaching of Attention Learners

  2026cites this paper
• Stealthy Poisoning Attacks Bypass Defenses in Regression Settings

  2026cites this paper
• Learning Management Systems as Anti-Convivial Tools

  2026cites this paper
• Positive Characteristic Sets for Relational Pattern Languages

  2025cites this paper
• Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation

  2025cites this paper
• Interaction-Driven Browsing: A Human-in-the-Loop Conceptual Framework Informed by Human Web Browsing for Browser-Using Agents

  2025cites this paper
• Nonparametric Teaching for Graph Property Learners

  2025cites this paper
• Training People to Reward Robots

  2025cites this paper
• SPECTRA: Personalizable Sound Recognition for Deaf and Hard of Hearing Users through Interactive Machine Learning

  2025cites this paper
• The Computational Complexity of Positive Non-Clashing Teaching in Graphs

  2025cites this paper
• Overcoming the Price of Anarchy by Steering with Recommendations

  2025cites this paper
• Dictionary Learning: The Complexity of Learning Sparse Superposed Features with Feedback

  2025cites this paper
• Optimal Task Order for Continual Learning of Multiple Tasks

  2025cites this paper
• Enabling Older Adults to Provide High-quality Activity Labels: Unpacking Accuracy, Precision, and Granularity in Activity Labeling

  2025cites this paper
• How Can Everyday Users Efficiently Teach Robots by Demonstration?

  2025cites this paper
• Novel and optimized mouse behavior enabled by fully autonomous HABITS: Home-cage assisted behavioral innovation and testing system

  2025influential citation
• Advancing 4‐Part Evolutionary Harmony Through Analysis of Human–Machine Approaches to Teaching–Learning

  2025cites this paper
• Representational Alignment Supports Effective Machine Teaching

  2024cites this paper
• Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning Models

  2024cites this paper
• Entity Examples for Explainable Query Target Type Identification with LLMs

  2024cites this paper
• Machine learning for modeling human decisions.

  2024cites this paper
• Computational Teaching for Driving via Multi-Task Imitation Learning

  2024cites this paper
• Using Machine Teaching to Boost Novices' Robot Teaching Skill

  2024cites this paper
• Transferring Domain Knowledge with (X)AI-Based Learning Systems

  2024influential citation
• Nonparametric Teaching of Implicit Neural Representations

  2024cites this paper
• Redefining Activity Tracking Through Older Adults' Reflections on Meaningful Activities

  2024cites this paper
• Toward In-Context Teaching: Adapting Examples to Students' Misconceptions

  2024cites this paper
• Proximal Curriculum with Task Correlations for Deep Reinforcement Learning

  2024cites this paper
• Comparing Teaching Strategies of a Machine Learning-based Prosthetic Arm

  2024cites this paper
• Exploring AI Problem Formulation with Children via Teachable Machines

  2024cites this paper
• On a Combinatorial Problem Arising in Machine Teaching

  2024cites this paper
• Clarify: Improving Model Robustness With Natural Language Corrections

  2024cites this paper
• Controlling human causal inference through in silico task design.

  2024cites this paper
• When Redundancy Matters: Machine Teaching of Representations

  2024cites this paper
• Nonparametric Teaching for Multiple Learners

  2023cites this paper
• Multi-Agent Strategy Explanations for Human-Robot Collaboration

  2023cites this paper
• Towards Effective Human-AI Decision-Making: The Role of Human Learning in Appropriate Reliance on AI Advice

  2023cites this paper
• Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind

  2023cites this paper
• XAI with Machine Teaching When Humans Are (Not) Informed About the Irrelevant Features

  2023cites this paper
• Interactively Teaching an Inverse Reinforcement Learner with Limited Feedback

  2023cites this paper
• Non-Clashing Teaching Maps for Balls in Graphs

  2023cites this paper
• Leading teachers' perspective on teacher-AI collaboration in education

  2023cites this paper
• MAP- and MLE-Based Teaching

  2023cites this paper
• Teaching to Learn: Sequential Teaching of Learners with Internal States

  2023cites this paper
• Heuristic search of optimal machine teaching curricula

  2023cites this paper
• Human Expectations and Perceptions of Learning in Machine Teaching

  2023cites this paper
• Nonparametric Iterative Machine Teaching

  2023influential citation
• ML-Based Teaching Systems: A Conceptual Framework

  2023influential citation
• Towards Professional Level Crowd Annotation of Expert Domain Data

  2023cites this paper
• Proximal Curriculum for Reinforcement Learning Agents

  2023cites this paper
• Learning Human-Compatible Representations for Case-Based Decision Support

  2023cites this paper
• How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement

  2023cites this paper
• The Inner Loop of Collective Human–Machine Intelligence

  2023cites this paper
• A Generalized Explanation Framework for Visualization of Deep Learning Model Predictions

  2023cites this paper
• The DataScope: A Mixed-Initiative Architecture for Data Labeling

  2022cites this paper
• Bayesian Adaptive Randomization with Compound Utility Functions

  2022cites this paper
• Time-Constrained Learning

  2022cites this paper
• Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning

  2022cites this paper
• Distinguishing Relational Pattern Languages With a Small Number of Short Strings

  2022cites this paper
• Reinforcement Teaching

  2022cites this paper
• Know Thy Student: Interactive Learning with Gaussian Processes

  2022cites this paper
• A Probabilistic Framework for Non-Cheating Machine Teaching ∗

  2022cites this paper
• Human-AI Interaction Design in Machine Teaching

  2022cites this paper
• Black-box Generalization of Machine Teaching

  2022cites this paper
• The Teaching Dimension of Regularized Kernel Learners

  2022cites this paper
• Sample Efficient Learning of Predictors that Complement Humans

  2022cites this paper
• Teaching Interactively to Learn Emotions in Natural Language

  2022cites this paper
• Non-Cheating Teaching Revisited: A New Probabilistic Machine Teaching Model

  2022cites this paper
• Learning Curricula for Humans: An Empirical Study with Puzzles from The Witness

  2022cites this paper
• Visual Knowledge Tracing

  2022cites this paper
• Gesture-aware Interactive Machine Teaching with In-situ Object Annotations

  2022cites this paper
• On the Fundamental Limits of Formally (Dis)Proving Robustness in Proof-of-Learning

  2022cites this paper
• Blind Users Accessing Their Training Images in Teachable Object Recognizers

  2022cites this paper
• Human-in-the-loop machine learning: a state of the art

  2022cites this paper
• Counterfactual Examples for Human Inverse Reinforcement Learning

  2022cites this paper
• Ethical conversational agent for performing in-game user experience questionnaires

  2022cites this paper
• Iterative Teaching by Data Hallucination

  2022cites this paper
• Bridging Human–Computer Interaction and Natural Language Processing

  2022cites this paper
• One-shot Machine Teaching: Cost Very Few Examples to Converge Faster

  2022influential citation
• Interactive Machine Learning for Multimodal Affective Computing

  2022cites this paper
• On Batch Teaching with Sample Complexity Bounded by VCD

  2022cites this paper
• When an Active Learner Meets a Black-box Teacher

  2022cites this paper
• Agent Smith: Teaching Question Answering to Jill Watson

  2021cites this paper
• Reinforcement Learning for Education: Opportunities and Challenges

  2021cites this paper
• Optimal Teaching Curricula with Compositional Simplicity Priors

  2021cites this paper
• A model of symbiomemesis: machine education and communication as pillars for human-autonomy symbiosis

  2021cites this paper
• Teaching Multiple Inverse Reinforcement Learners

  2021cites this paper
• Exploring Machine Teaching with Children

  2021influential citation
• Iterative Teaching by Label Synthesis

  2021cites this paper
• Teaching an Active Learner with Contrastive Examples

  2021cites this paper
• Integrating Iterative Machine Teaching and Active Learning into the Machine Learning Loop

  2021cites this paper
• A Machine Teaching Framework for Scalable Recognition

  2021cites this paper
• Teaching Humans When To Defer to a Classifier via Examplars

  2021cites this paper
• A machine education approach to swarm decision-making in best-of-n problems

  2021cites this paper
• Agent Smith: Machine Teaching for Building Question Answering Agents

  2021cites this paper
• Gradient-based Algorithms for Machine Teaching

  2021cites this paper
• Curriculum Design for Teaching via Demonstrations: Theory and Applications

  2021cites this paper
• Bayesian Persuasion in Sequential Decision-Making

  2021cites this paper
• Locality Sensitive Teaching

  2021cites this paper
• Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm

  2021cites this paper