Artificial Neural Networks as Feature Extractors in Continuous Evolutionary Optimization

Friess，Stephen1; Tino，Peter1; Xu，Zhao2; Menzel，Stefan3; Sendhoff，Bernhard3; Yao，Xin1,4

10.1109/IJCNN52387.2021.9533915

2021-07-18

International Joint Conference on Neural Networks (IJCNN)

2161-4393

978-1-6654-4597-9

Proceedings of the International Joint Conference on Neural Networks

2021-July

1-9

JUL 18-22, 2021

null,null,ELECTR NETWORK

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Recent years have seen the advancement of data-driven paradigms in population-based and evolutionary optimization. This reflects on one hand the mere abundance of available data, but on the other hand also progresses in the refinement of previously available machine learning methods. Surprisingly, deep pattern recognition methods emerging from the studies of neural networks have only been sparingly applied. This comes unexpected, as the complex data generated by evolutionary search algorithms can be considered tedious and intractable for manual analysis with mere practical intuitions. In this work, we therefore explore opportunities to employ deep networks to directly learn problem characteristics of continuous optimization problems. Particularly, with data obtained during initial runs of an optimization algorithm. We find that a graph neural network, trained upon a graph representation of continuous search spaces, shows in comparison to more traditional approaches higher validation accuracy and retrieves characteristics within the latent space which are better at distinguishing different continuous optimization problems. We hope that our study can pave the way towards new approaches which allow us to learn problem-dependent algorithm components and recall these from predictions of inputs generated during the run-time of an optimization algorithm.

algorithm selection Feature learning graph neural networks knowledge transfer representation learning

其他

英语

CPCI-S ; EI

European Union[766186]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic

WOS:000722581704121

20214110995924

Evolutionary algorithms ; Knowledge management ; Learning algorithms ; Learning systems ; Neural networks ; Optimization ; Pattern recognition ; Population statistics

Artificial Intelligence:723.4 ; Machine Learning:723.4.2 ; Computer Applications:723.5 ; Information Retrieval and Use:903.3 ; Optimization Techniques:921.5

2-s2.0-85116461693

Scopus

1.University of Birmingham,Cercia,School of Computer Science,United Kingdom
2.Nec Laboratories Europe GmbH,Heidelberg,69115,Germany
3.Honda Research Institute Europe GmbH,Offenbach,63073,Germany
4.Southern University of Science and Technology,Shenzhen,China

Friess，Stephen,Tino，Peter,Xu，Zhao,et al. Artificial Neural Networks as Feature Extractors in Continuous Evolutionary Optimization[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021:1-9.