Our mission is to explore and establish a methodology for evolutionary intelligence that fosters highly adaptive, autonomous, and theoretically reliable learning and optimization abilities. Our current research topics include the followings:
Expensive optimization
Many real-world applications require optimizing expensive-to-evaluate objectives, as objective values are evaluated often with computationally expensive simulations or costly experiments. An example is the optimization of aircraft wing using CFD simulation, which is computationally expensive. To solve such expensive optimization problems, we explore sample-efficient optimization techniques. Especially, high-dimensional multi-objective problems are our main focus to be studied.Evolutionary machine learning
Integrating meta-heuristics into machine learning approaches bring highly adaptive and autonomous ability, such as auto-design of learning models, auto-tuning of hyper-parameters, and extraction of explainable models. We explore evolutionary machine leaning techniques; evolutionary rule-based learning, evolutionary symbolic regression, evolutionary neural architecture search, and etc. We are interested in realizing the interplay between evolution and learning on a computer intelligence scheme.-
16 February 2024 We have proposed a novel approximation-based multiobjective evolutionary algorithm to solve high-dimensional expensive multi-objective optimization problems. A main finding is that constructing an approximation model for each single-objective decomposed problem can be a reasonable strategy to address the high-dimensionality of problems. The proposed algorithm can drive state-of-the-art performance compared to modern algorithms. This contribution has been published on Swarm and Evolutionary Computation. paper code
-
29 December 2023 While there are few effective optimization algorithms for moderately expensive single-objective optimization problems, we have proposed a fast and easy-to-use adaptive evolutionary algorithm that efficiently samples and automatically tunes its hyperparameters, by emulating the principle of sample-efficient optimization algorithms such as surrogate-assisted evolutionary algorithms. Experimental results also showed that surrogate-assisted evolutionary algorithms suffer from premature convergence and unnecessarily long runtimes in moderately expensive optimization problems. This contribution has been published on Complex & Intelligent Systems. paper code
-
14 March 2022 We proposed a surrogate-assisted multiobjective evolutionary algorithm, which utilizes classification models adapted to single-objective decomposed problems, for solving high-dimensional expensive multi-objective optimization problems. Experimental results confirm that the proposed algorithm is competitive to the state-of-the-art algorithms and computationally efficient as well. This contribution has been published on IEEE Transactions on Evolutionary Computation. paper code
-
13 February 2021 Evolutionary Rule-based Learning (ERML) approaches have been applied to modern issues in the machine learning field. We have derived a theoretical approach that mathematically guarantees that ERML identifies maximally accurate rules in the fewest iterations possible, which also returns a theoretically valid hyper-parameter setting. We also experimentally show that our theoretical setting enables ERML to easily solve several challenging problems where it had previously struggled. This contribution has been published on IEEE Transactions on Evolutionary Computation. paper code
Our laboratory is on the eighth floor of N6-2, Hodogaya-campus, Yokohama National University. See here for more detail.
- Affiliation Faculty of Engineering, Yokohama National University
- Address Room 801/812, N6-2, Tokiwadai 79-5, Yokohama, Japan, 240-8501.
- E-mail nakata-masaya-tb at ynu.ac.jp(to Masaya Nakata)