Novel surrogate measures based on a similarity network for neural architecture search

Kus, Zeki and Akkan, Can and Gulcu, Ayla (2023) Novel surrogate measures based on a similarity network for neural architecture search. IEEE Access, 11 . pp. 22596-22613. ISSN 2169-3536

Full text not available from this repository. (Request a copy)


We propose two novel surrogate measures to predict the validation accuracy of the classification produced by a given neural architecture, thus eliminating the need to train it, in order to speed up neural architecture search (NAS). The surrogate measures are based on a solution similarity network, where distance between solutions is measured using the binary encoding of some graph sub-components of the neural architectures. These surrogate measures are implemented within local search and differential evolution algorithms and tested on NAS-Bench-101 and NAS-Bench-301 datasets. The results show that the performance of the similarity-network-based predictors, as measured by correlation between predicted and true accuracy values, are comparable to the state-of-the-art predictors in the literature, however they are significantly faster in achieving these high correlation values for NAS-Bench-101. Furthermore, in some cases, the use of these predictors significantly improves the search performance of the equivalent algorithm (differential evolution or local search) that does not use the predictor.
Item Type: Article
Uncontrolled Keywords: Benchmark testing; Computational modeling; Computer architecture; Correlation; Encoding; evolutionary algorithm; neural architecture search; Prediction algorithms; Predictive models; similarity-based prediction; surrogate model
Divisions: Sabancı Business School
Depositing User: Can Akkan
Date Deposited: 07 May 2023 20:16
Last Modified: 07 May 2023 20:16

Actions (login required)

View Item
View Item