A Genetic Algorithm with Tree-structured Mutation for Hyperparameter Optimisation of Graph Neural Networks

Yingfang Yuan, Wenjun Wang, Wei Pang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)
121 Downloads (Pure)

Abstract

In recent years, graph neural networks (GNNs) have gained increasing attention, as they possess the excellent capability of processing graph-related problems. In practice, hyperparameter optimisation (HPO) is critical for GNNs to achieve satisfactory results, but this process is costly because the evaluations of different hyperparameter settings require excessively training many GNNs. Many approaches have been proposed for HPO, which aims to identify promising hyperparameters efficiently. In particular, the genetic algorithm (GA) for HPO has been explored, which treats GNNs as a black-box model, of which only the outputs can be observed given a set of hyperparameters. However, because GNN models are sophisticated and the evaluations of hyperparameters on GNNs are expensive, GA requires advanced techniques to balance the exploration and exploitation of the search and make the optimisation more effective given limited computational resources. Therefore, we proposed a tree-structured mutation strategy for GA to alleviate this issue. Meanwhile, we reviewed the recent HPO works, which gives room for the idea of tree-structure to develop, and we hope our approach can further improve these HPO methods in the future.
Original languageEnglish
Title of host publication2021 IEEE Congress on Evolutionary Computation (CEC)
PublisherIEEE
Pages482-489
Number of pages9
ISBN (Electronic)9781728183930
DOIs
Publication statusPublished - 9 Aug 2021
Event 2021 IEEE Congress on Evolutionary Computation - Krakow, Poland
Duration: 28 Jun 20211 Jul 2021

Conference

Conference 2021 IEEE Congress on Evolutionary Computation
Abbreviated titleCEC 2021
Country/TerritoryPoland
CityKrakow
Period28/06/211/07/21

Fingerprint

Dive into the research topics of 'A Genetic Algorithm with Tree-structured Mutation for Hyperparameter Optimisation of Graph Neural Networks'. Together they form a unique fingerprint.

Cite this