Enhancing generalization in genetic programming hyper-heuristics through mini-batch sampling strategies for dynamic workflow scheduling

Created by W.Langdon from gp-bibliography.bib Revision:1.8414

@Article{Yang:2024:ins,

• author = "Yifan Yang and Gang Chen and Hui Ma and Sven Hartmann and Mengjie Zhang",
• title = "Enhancing generalization in genetic programming hyper-heuristics through mini-batch sampling strategies for dynamic workflow scheduling",
• journal = "Information Sciences",
• year = "2024",
• volume = "678",
• pages = "120975",
• keywords = "genetic algorithms, genetic programming, Dynamic workflow scheduling, Genetic programming hyper-heuristics, Generalization, Mini-batch",
• ISSN = "0020-0255",
• URL = "https://www.sciencedirect.com/science/article/pii/S0020025524008892",
• DOI = "doi:10.1016/j.ins.2024.120975",
• abstract = "Genetic Programming Hyper-heuristics (GPHH) have been successfully used to evolve scheduling rules for Dynamic Workflow Scheduling (DWS) as well as other challenging combinatorial optimisation problems. The method of sampling training instances has a significant impact on the generalisation ability of GPHH, yet they are rarely addressed in existing research. This article aims to fill this gap by proposing a GPHH algorithm with a sampling strategy to thoroughly investigate the impact of six instance sampling strategies on algorithmic generalisation, including one rotation strategy, three mini-batch strategies, and two hybrid strategies. Experiments across four scenarios with varying settings reveal that: (1) mini-batch with random sampling can outperform rotation in generalizing to unseen workflow scheduling problems under the same computational cost; (2) employing a hybrid strategy that combines rotation and mini-batch further enhances the generalisation ability of GPHH; and (3) mini-batch and hybrid strategies can effectively enable heuristics trained on small-scale training instances generalizing well to large-scale unseen ones. These findings highlight the potential of mini-batch strategies in GPHH, offering improved generalisation performance while maintaining diversity and suggesting promising avenues for further exploration in GPHH domains",

}

Genetic Programming entries for Yifan Yang Gang Chen Hui Ma Sven Hartmann Mengjie Zhang

Citations