Graph Embedding Comparator for Evolutionary Neural Architecture Search with Isomorphic Multi-Comparison
International Journal of Neural Systems · 2026-05 · 36 (05)
DOI: 10.1142/s0129065726500097 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Neural Systems, online erschienen am 26.01.2026. Verfasst von Xiaolei Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Software, Nanjing University of Information Science and Technology, Nanjing 210044, P. R. China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: the National Natural Science Foundation of China, the Natural Science Foundation of Jiangsu Province, the Postgraduate Research & Practice Innovation Program of Jiangsu Province.
Abstract (Originalsprache)
Designing effective neural architectures remains a central challenge in deep learning, and Neural Architecture Search (NAS) has become a popular tool for automating this process. However, many existing NAS approaches depend on hand-crafted architecture descriptors or shallow performance predictors, which fail to capture the structural complexity of candidate networks and often lead to unreliable search guidance. We introduce Graph Embedding Comparator with Isomorphic Multi-Comparison (GEC-IMC), an evolutionary NAS framework that learns architecture representations directly from their graph structure. A graph convolutional network encodes architectures into embeddings, while a contrastive learning strategy ensures that architectures with similar accuracy are mapped closer in the embedding space. On top of these embeddings, a comparator estimates the relative performance between two architectures, enabling more precise pairwise assessments during search. To further increase robustness, GEC-IMC incorporates an isomorphic multi-comparison mechanism, which evaluates multiple structurally equivalent variants of each architecture and aggregates their pairwise outcomes into a global score. This ranking score provides consistent feedback for evolutionary selection. Experiments on standard NAS benchmarks demonstrate that GEC-IMC achieves state-of-the-art performance with improved robustness over existing predictors. Ablation studies confirm the complementary roles of embedding learning and multi-comparison in enhancing search efficiency.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Software, Nanjing University of Information Science and Technology, Nanjing 210044, P. R. China.
- NICE Research Group, School of Computer Science and Electronic Engineering, University of Surrey, Guildford GU2 7XS, UK.
- Nanjing University of Information Science and Technology, Nanjing 210044, P. R. China.
ORCID-Profile: Xiaolei Zhang, Yu Xue, Ferrante Neri
Förderung
- the National Natural Science Foundation of China
- the Natural Science Foundation of Jiangsu Province
- the Postgraduate Research & Practice Innovation Program of Jiangsu Province
- the Natural Science Foundation of the Jiangsu Higher Education Institutions of China
Zitieren
APA
Zhang, X., Xue, Y., & Neri, F. (2026). Graph Embedding Comparator for Evolutionary Neural Architecture Search with Isomorphic Multi-Comparison. International Journal of Neural Systems, 36(05). https://doi.org/10.1142/s0129065726500097
Vancouver
Zhang X, Xue Y, Neri F. Graph Embedding Comparator for Evolutionary Neural Architecture Search with Isomorphic Multi-Comparison. International Journal of Neural Systems. 2026;36(05). doi:10.1142/s0129065726500097
BibTeX
@article{Zhang2026,
author = {Zhang, Xiaolei and Xue, Yu and Neri, Ferrante},
title = {Graph Embedding Comparator for Evolutionary Neural Architecture Search with Isomorphic Multi-Comparison},
journal = {International Journal of Neural Systems},
year = {2026},
volume = {36},
number = {05},
doi = {10.1142/s0129065726500097}
}
EUVIMED