IEEE Transactions on Evolutionary Computation, Volume 30, Issue 1, February 2025

2026-02-04 · Source: Computational Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Data Science & Analytics · Depth: Advanced, short

Summary

The IEEE Transactions on Evolutionary Computation, Volume 30, Issue 1, published in February 2025, presents 31 research articles covering advancements in evolutionary algorithms and their applications. Key topics include decomposition-based evolutionary algorithms for multiobjective fuzzy flexible jobshop scheduling, enhancing genetic algorithms with explainable AI for last-mile routing, and learning to preselection for multiobjective feature selection in classification. Other contributions explore optimal linear crossover for mitigating negative transfer in evolutionary multitasking, niching genetic programming for deep reinforcement learning in dynamic flexible scheduling, and comprehensive-forecast multiobjective genetic programming for neural architecture search. The volume also features work on particle-assisted deep reinforcement learning for quantum state manipulation, evolutionary multiobjective spiking neural architecture search for image classification, and a survey on evolutionary feature selection in multilabel classification. Further articles address evolving differential evolution, speeding up local search, imitation learning-assisted algorithms for energy-efficient job shop scheduling, and data-driven evolutionary algorithms based on inductive graph neural networks for multimodal multiobjective optimization.

Key takeaway

For research scientists developing advanced optimization solutions, this volume highlights critical trends in integrating evolutionary algorithms with deep learning and explainable AI. You should explore methods like decomposition-based EAs for complex scheduling and consider neural architecture search via multiobjective genetic programming to enhance model performance and efficiency.

Key insights

Evolutionary computation continues to advance, integrating with AI and deep learning for complex optimization and scheduling tasks.

Principles

• Decomposition enhances multiobjective optimization.
• Explainable AI improves genetic algorithm transparency.
• Transfer learning mitigates negative transfer.

Method

Several papers propose methods like hierarchical estimation for scheduling, filter-based performance prediction for feature selection, and bi-knowledge transfer for multimodal optimization.

In practice

• Apply EAs to fuzzy flexible jobshop scheduling.
• Use XAI to explain last-mile routing decisions.
• Employ GNNs for multimodal optimization.

Topics

• Evolutionary Computation
• Multiobjective Optimization
• Neural Architecture Search
• Genetic Algorithms
• Reinforcement Learning

Best for: Research Scientist, AI Researcher, AI Scientist, AI Engineer

Related on AIssential

• IEEE Transactions on Evolutionary Computation, Volume 30, Issue 2, April 2025 — Evolutionary algorithms and multiobjective optimization are advancing diverse fields from logistics to AI design.
• Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach — ILASP can approximate black-box Neural Networks for preference learning, even in high-dimensional spaces.
• IEEE Transactions on Neural Networks and Learning Systems, Volume 37, Issue 4, April 2026 — The volume showcases diverse neural network and learning system advancements across various applications and theoretical foundations.
• Distribution-Free Pretraining of Classification Losses via Evolutionary Dynamics — EDL pretrains transferable classification losses using synthetic data and evolutionary optimization with chaotic mutation.
• Scaling Neuro-symbolic Problem Solving: Solver-Free Learning of Constraints and Objectives — A neuro-symbolic architecture with a probabilistic loss efficiently learns to solve NP-hard problems from natural inputs.
• Associative Constructive Evolution: Enhancing Metaheuristics through Hebbian-Learned Generative Guidance — ACE enhances metaheuristics by learning and reusing successful operation patterns through a generative automaton.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Computational Intelligence.