Active Learning-Based Optimization of Scientific Experimental Design

TL;DR

This paper demonstrates that active learning can optimize scientific experimental design, reducing human effort and improving efficiency through a novel query strategy that outperforms traditional sampling methods.

Contribution

It introduces an active learning framework combining ALS and DNN for experimental design and proposes a new expected loss minimization query strategy.

Findings

AL improves experimental efficiency over manual design

ELM sampling outperforms random and uncertainty sampling

Retrospective study validates the approach's effectiveness

Abstract

Active learning (AL) is a machine learning algorithm that can achieve greater accuracy with fewer labeled training instances, for having the ability to ask oracles to label the most valuable unlabeled data chosen iteratively and heuristically by query strategies. Scientific experiments nowadays, though becoming increasingly automated, are still suffering from human involvement in the designing process and the exhaustive search in the experimental space. This article performs a retrospective study on a drug response dataset using the proposed AL scheme comprised of the matrix factorization method of alternating least square (ALS) and deep neural networks (DNN). This article also proposes an AL query strategy based on expected loss minimization. As a result, the retrospective study demonstrates that scientific experimental design, instead of being manually set, can be optimized by AL, and the proposed query strategy ELM sampling shows better experimental performance than other ones such as random sampling and uncertainty sampling.