EGNAS: Efficient Graph Neural Architecture Search Through Evolutionary Algorithm

Younkyung Jwa, Chang Wook Ahn () and Man-Je Kim ()
Additional contact information
Younkyung Jwa: AI Graduate School, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea
Chang Wook Ahn: AI Graduate School, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea
Man-Je Kim: Convergence of AI, Chonnam National University, Gwangju 61186, Republic of Korea

Mathematics, 2024, vol. 12, issue 23, 1-14

Abstract: The primary objective of our research is to enhance the efficiency and effectiveness of Neural Architecture Search (NAS) with regard to Graph Neural Networks (GNNs). GNNs have emerged as powerful tools for learning from unstructured network data, compensating for several known limitations of Convolutional Neural Networks (CNNs). However, the automatic search for optimal GNN architectures has seen little progressive advancement so far. To address this gap, we introduce the Efficient Graph Neural Architecture Search (EGNAS), a method that leverages the advantages of evolutionary search strategies. EGNAS incorporates inherited parameter sharing, allowing offspring to inherit parameters from their parents, and utilizes half epochs to improve optimization stability. In addition, EGNAS employs a combined evolutionary search, which explores both the model structure and the hyperparameters within a large search space, resulting in improved performance. Our experimental results demonstrate that EGNAS outperforms state-of-the-art methods in node classification tasks on the Cora, Citeseer, and PubMed datasets while maintaining a high degree of computational efficiency. In particular, EGNAS is the fastest GNN architecture search method in terms of search time, particularly when compared to precedently suggested evolutionary search strategies, delivering performance up to 40 times faster.

Keywords: graph neural network; neural architecture search; evolutionary neural architecture search (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/23/3828/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/23/3828/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:23:p:3828-:d:1536171

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().