Active Learning-Based Optimization of Scientific Experimental Design
This work addresses the inefficiency in designing scientific experiments, offering a domain-specific improvement for automated experimental processes.
The paper tackles the problem of optimizing scientific experimental design by using active learning to reduce human involvement and exhaustive search, demonstrating that the proposed expected loss minimization query strategy outperforms random and uncertainty sampling in a drug response dataset.
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.