Novelty driven evolutionary neural architecture search

Nilotpal Sinha, Kuan Wen Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


Evolutionary algorithms (EA) based neural architecture search (NAS) involves evaluating each architecture by training it from scratch, which is extremely time-consuming. This can be reduced by using a supernet for estimating the fitness of an architecture due to weight sharing among all architectures in the search space. However, the estimated fitness is very noisy due to the co-adaptation of the operations in the supernet which results in NAS methods getting trapped in local optimum. In this paper, we propose a method called NEvoNAS wherein the NAS problem is posed as a multi-objective problem with 2 objectives: (i) maximize architecture novelty, (ii) maximize architecture fitness/accuracy. The novelty search is used for maintaining a diverse set of solutions at each generation which helps avoiding local optimum traps while the architecture fitness is calculated using supernet. NSGA-II is used for finding the pareto optimal front for the NAS problem and the best architecture in the pareto front is returned as the searched architecture. Exerimentally, NEvoNAS gives better results on 2 different search spaces while using significantly less computational resources as compared to previous EA-based methods. The code for our paper can be found here.

Original languageEnglish
Title of host publicationGECCO 2022 Companion - Proceedings of the 2022 Genetic and Evolutionary Computation Conference
PublisherAssociation for Computing Machinery, Inc
Number of pages4
ISBN (Electronic)9781450392686
StatePublished - 9 Jul 2022
Event2022 Genetic and Evolutionary Computation Conference, GECCO 2022 - Virtual, Online, United States
Duration: 9 Jul 202213 Jul 2022

Publication series

NameGECCO 2022 Companion - Proceedings of the 2022 Genetic and Evolutionary Computation Conference


Conference2022 Genetic and Evolutionary Computation Conference, GECCO 2022
Country/TerritoryUnited States
CityVirtual, Online


  • multi-objective optimization
  • neural architecture search
  • novelty search
  • supernet


Dive into the research topics of 'Novelty driven evolutionary neural architecture search'. Together they form a unique fingerprint.

Cite this