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

TL;DR

This paper introduces a one-shot machine teaching paradigm that minimizes teaching examples and accelerates convergence by establishing a surjective mapping from teaching sets to model parameters, supported by theoretical guarantees and experimental validation.

Contribution

It proposes a novel one-shot machine teaching framework with a surjective mapping, enabling efficient and minimal teaching sets for faster model convergence.

Findings

Theoretical proof of surjective mapping guarantees existence of optimal teaching sets.

Development of a strategy for designing optimal teaching sets based on efficiency metrics.

Experimental results demonstrate the effectiveness and efficiency of the proposed teaching paradigm.

Abstract

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.