Rui P Cardoso
Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers
Cardoso, Rui P; Hart, Emma; Burth Kurka, David; Pitt, Jeremy
Prof Emma Hart E.Hart@napier.ac.uk
David Burth Kurka
Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification. However, using gradient descent to train evolved architectures during the search can be computationally prohibitive. Here we propose a method to overcome this limitation by using a surrogate model which estimates the behavioural distance between two neural network architectures required to calculate the sparseness term in Novelty Search. We demonstrate a speedup of 10 times over previous work and significantly improve on previous reported results on three benchmark datasets from Computer Vision-CIFAR-10, CIFAR-100, and SVHN. This results from the expanded architecture search space facilitated by using a surrogate. Our method represents an improved paradigm for implementing horizontal scaling of learning algorithms by making an explicit search for diversity considerably more tractable for the same bounded resources.
Cardoso, R. P., Hart, E., Burth Kurka, D., & Pitt, J. (2022). Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers. In Applications of Evolutionary Computation: EvoApplications 2022 (418-434). https://doi.org/10.1007/978-3-031-02462-7_27
|Start Date||Apr 20, 2022|
|End Date||Apr 22, 2022|
|Acceptance Date||Jan 26, 2022|
|Online Publication Date||Apr 15, 2022|
|Deposit Date||Feb 7, 2022|
|Publicly Available Date||Apr 16, 2023|
|Series Title||Lecture Notes in Computer Science|
|Book Title||Applications of Evolutionary Computation: EvoApplications 2022|
|Keywords||diversity, ensemble, novelty search, surrogate|
This file is under embargo until Apr 16, 2023 due to copyright reasons.
Contact email@example.com to request a copy for personal use.
You might also like
Evolutionary Approaches to Improving the Layouts of Instance-Spaces
Morpho-evolution with learning using a controller archive as an inheritance mechanism