Iterative Machine Teaching

TL;DR

This paper introduces a new iterative machine teaching paradigm where teachers sequentially feed examples to learners, significantly reducing teaching complexity and accelerating convergence compared to traditional batch methods.

Contribution

It develops a novel iterative teaching framework with algorithms that adaptively select examples, demonstrating faster convergence and lower teaching complexity.

Findings

Iterative teaching reduces the number of examples needed for convergence.

Algorithms adaptively select examples based on learner performance.

Experimental results validate theoretical improvements across datasets.

Abstract

In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learner. We show that the teaching complexity in the iterative case is very different from that in the batch case. Instead of constructing a minimal training set for learners, our iterative machine teaching focuses on achieving fast convergence in the learner model. Depending on the level of information the teacher has from the learner model, we design teaching algorithms which can provably reduce the number of teaching examples and achieve faster convergence than learning without teachers. We also validate our theoretical findings with extensive experiments on different data distribution and real image datasets.