Szczegóły publikacji
Opis bibliograficzny
SA-LGP: Surrogate-Assisted Linear Genetic Programming for evolving graph neural networks for node classification / Maciej KRZYWDA, Szymon ŁUKASIK, Amir H. Gandomi // W: GECCO'26 Companion [Dokument elektroniczny] : proceedings of the 2026 Genetic and Evolutionary Computation Conference : San Jose, Costa Rica, July 13–17, 2026 / eds. Leonardo Trujillo, Ting Hu. — Wersja do Windows. — Dane tekstowe. — New York : Association for Computing Machinery, cop. 2026. — e-ISBN: 979-8-4007-2488-6. — S. 1601–1607. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 1607, Abstr. — Publikacja dostępna online od: 2026-08-13. — Sz. Łukasik - dod. afiliacje: Systems Research Institute Polish Academy of Sciences, Warsaw ; NASK National Research Institute, Warsaw
Autorzy (3)
- AGHKrzywda Maciej
- AGHŁukasik Szymon
- Gandomi Amir H.
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 169651 |
|---|---|
| Data dodania do BaDAP | 2026-09-29 |
| Tekst źródłowy | URL |
| DOI | 10.1145/3795101.3814679 |
| Rok publikacji | 2026 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Creative Commons | |
| Wydawca | Association for Computing Machinery (ACM) |
| Konferencja | Genetic and Evolutionary Computations 2026 |
Abstract
Neural Architecture Search (NAS) aims to automate the design of neural network architectures, reducing reliance on manual engineering. Evolutionary approaches provide flexible search mechanisms but suffer from high computational cost due to expensive fitness evaluations. In this paper, we propose a Surrogate-Assisted Linear Genetic Programming (SA-LGP) framework for automated design of Graph Neural Network (GNN) architectures for node classification. Unlike conventional NAS methods based on fixed-length or graph-structured encodings, our approach employs variable-length linear genetic programs to construct architectures composed of diverse message-passing layers and regularization operators. To reduce computational cost, we introduce a pairwise surrogate model that predicts whether an offspring architecture is likely to outperform its parent using genotype-derived features and early training signals. The surrogate acts as a filter within the evolutionary loop, enabling full evaluation only for promising candidates. A two-stage evaluation protocol is used, consisting of a cheap early-training phase and a full-training phase for selected architectures. Experiments on benchmark graph datasets show that SA-LGP discovers compact and competitive GNN architectures while significantly reducing the number of expensive evaluations, demonstrating the effectiveness of surrogate-assisted evolutionary search.
