Introduction to the special issue on explainable AI in evolutionary computation: part 2

Bacardit, Jaume; Brownlee, Alexander; Cagnoni, Stefano; Iacca, Giovanni; McCall, John; Walker, David

Abstract

Explainable AI (XAI) has gained significant traction in the machine learning community in recent years because of the need to generate 'explanations' of how these typical black-box tools operate that are accessible to a wide range of users. Likewise, nature-inspired optimisation techniques, such as Evolutionary Computation (EC) algorithms, are also often black box in nature, so the EC community has begun to consider explaining their algorithms, too. Despite these common aspects, the intersection between EC and XAI (in short, ECXAI) is still rather unexplored. This topic is the subject of our Workshops on Evolutionary Computing and Explainable Artificial Intelligence (ECXAI) organised yearly since GECCO 2022. In March 2024, we edited the first part of a Special Issue on Explainable AI in Evolutionary Computation. Due to the large number of submissions received and the growing interest in this topic, we collect here a second issue of four papers that further explore the intersection between XAI and EC. This includes both the use of EC for XAI, as well as the use of explainability techniques to better understand EC methods.

• Journal Article Type: Editorial
• Acceptance Date: Apr 27, 2025
• Online Publication Date: May 16, 2025
• Publication Date: Jun 30, 2025
• Deposit Date: Jun 12, 2025
• Publicly Available Date: Jun 12, 2025
• Journal: ACM transactions on evolutionary learning and optimization
• Print ISSN: 2688-299X
• Electronic ISSN: 2688-3007
• Publisher: Association for Computing Machinery (ACM)
• Peer Reviewed: Peer Reviewed
• Volume: 5
• Issue: 2
• DOI: https://doi.org/10.1145/3733611
• Keywords: Explainable AI (XAI); Evolutionary computation (EC) algorithms
• Public URL: https://rgu-repository.worktribe.com/output/2879367