Outputs (97)

Automated design of local search algorithms: Predicting algorithmic components with LSTM (2023)
Journal Article
Meng, W., & Qu, R. (2024). Automated design of local search algorithms: Predicting algorithmic components with LSTM. Expert Systems with Applications, 237(Part A), Article 121431. https://doi.org/10.1016/j.eswa.2023.121431

With a recently defined AutoGCOP framework, the design of local search algorithms has been defined as the composition of elementary algorithmic components. The effective compositions of the best algorithms thus retain useful knowledge of effective al... Read More about Automated design of local search algorithms: Predicting algorithmic components with LSTM.

Automated design of search algorithms based on reinforcement learning (2023)
Journal Article
Yi, W., & Qu, R. (2023). Automated design of search algorithms based on reinforcement learning. Information Sciences, 649, Article 119639. https://doi.org/10.1016/j.ins.2023.119639

Automated algorithm design has attracted increasing research attention recently in the evolutionary computation community. The main design decisions include selection heuristics and evolution operators in the search algorithms. Most existing studies,... Read More about Automated design of search algorithms based on reinforcement learning.

Deep Contrastive Representation Learning With Self-Distillation (2023)
Journal Article
Xiao, Z., Xing, H., Zhao, B., Qu, R., Luo, S., Dai, P., Li, K., & Zhu, Z. (2024). Deep Contrastive Representation Learning With Self-Distillation. IEEE Transactions on Emerging Topics in Computational Intelligence, 8(1), 3-15. https://doi.org/10.1109/tetci.2023.3304948

Recently, contrastive learning (CL) is a promising way of learning discriminative representations from time series data. In the representation hierarchy, semantic information extracted from lower levels is the basis of that captured from higher level... Read More about Deep Contrastive Representation Learning With Self-Distillation.

Guest Editorial Special Issue on Multiobjective Evolutionary Optimization in Machine Learning (2023)
Journal Article
Aickelin, U., Khorshidi, H. A., Qu, R., & Charkhgard, H. (2023). Guest Editorial Special Issue on Multiobjective Evolutionary Optimization in Machine Learning. IEEE Transactions on Evolutionary Computation, 27(4), 746-748. https://doi.org/10.1109/tevc.2023.3292528

We are very pleased to introduce this special issue on multiobjective evolutionary optimization for machine learning (MOML). Optimization is at the heart of many machine-learning techniques. However, there is still room to exploit optimization in mac... Read More about Guest Editorial Special Issue on Multiobjective Evolutionary Optimization in Machine Learning.

Sequential Rule Mining for Automated Design of Meta-heuristics (2023)
Presentation / Conference Contribution
Meng, W., & Qu, R. (2023, July). Sequential Rule Mining for Automated Design of Meta-heuristics. Presented at GECCO 2023 Companion - Proceedings of the 2023 Genetic and Evolutionary Computation Conference Companion, New York, USA

With a recently defined AutoGCOP framework, the design of local search algorithms can be defined as the composition of the basic elementary algorithmic components. These compositions into the best algorithms thus retain useful knowledge of effective... Read More about Sequential Rule Mining for Automated Design of Meta-heuristics.

Models of Representation in Computational Intelligence [Guest Editorial] (2023)
Journal Article
Nobile, M. S., Manzoni, L., Ashlock, D. A., & Qu, R. (2023). Models of Representation in Computational Intelligence [Guest Editorial]. IEEE Computational Intelligence Magazine, 18(1), 20-21. https://doi.org/10.1109/MCI.2022.3223482

Computational Intelligence (CI) provides a set of powerful tools to effectively tackle complex computational tasks: global optimization methods (e.g., evolutionary computation, swarm intelligence), machine learning (e.g., neural networks), fuzzy reas... Read More about Models of Representation in Computational Intelligence [Guest Editorial].

Automated algorithm design using proximal policy optimisation with identified features (2022)
Journal Article
Yi, W., Qu, R., & Jiao, L. (2023). Automated algorithm design using proximal policy optimisation with identified features. Expert Systems with Applications, 216, Article 119461. https://doi.org/10.1016/j.eswa.2022.119461

Automated algorithm design is attracting considerable recent research attention in solving complex combinatorial optimisation problems, due to that most metaheuristics may be particularly effective at certain problems or certain instances of the same... Read More about Automated algorithm design using proximal policy optimisation with identified features.

Cooperative Double-Layer Genetic Programming Hyper-Heuristic for Online Container Terminal Truck Dispatching (2022)
Journal Article
Chen, X., Bai, R., Qu, R., & Dong, H. (2023). Cooperative Double-Layer Genetic Programming Hyper-Heuristic for Online Container Terminal Truck Dispatching. IEEE Transactions on Evolutionary Computation, 27(5), 1220-1234. https://doi.org/10.1109/TEVC.2022.3209985

In a marine container terminal, truck dispatching is a crucial problem that impacts on the operation efficiency of the whole port. Traditionally, this problem is formulated as an offline optimisation problem, whose solutions are, however, impractical... Read More about Cooperative Double-Layer Genetic Programming Hyper-Heuristic for Online Container Terminal Truck Dispatching.

An Efficient Federated Distillation Learning System for Multitask Time Series Classification (2022)
Journal Article
Xing, H., Xiao, Z., Qu, R., Zhu, Z., & Zhao, B. (2022). An Efficient Federated Distillation Learning System for Multitask Time Series Classification. IEEE Transactions on Instrumentation and Measurement, 71, https://doi.org/10.1109/TIM.2022.3201203

This paper proposes an efficient federated distillation learning system (EFDLS) for multi-task time series classification (TSC). EFDLS consists of a central server and multiple mobile users, where different users may run different TSC tasks. EFDLS ha... Read More about An Efficient Federated Distillation Learning System for Multitask Time Series Classification.

Automated Design of Metaheuristics Using Reinforcement Learning within a Novel General Search Framework (2022)
Journal Article
Yi, W., Qu, R., Jiao, L., & Niu, B. (2023). Automated Design of Metaheuristics Using Reinforcement Learning within a Novel General Search Framework. IEEE Transactions on Evolutionary Computation, 27(4), 1072-1084. https://doi.org/10.1109/TEVC.2022.3197298

Metaheuristic algorithms have been investigated intensively to address highly complex combinatorial optimisation problems. However, most metaheuristic algorithms have been designed manually by researchers of different expertise without a consistent f... Read More about Automated Design of Metaheuristics Using Reinforcement Learning within a Novel General Search Framework.