A Survey of Graph Transformers: Architectures, Theories and Applications
ACM Computing Surveys · 30.11.2026 · 58 (15) · 1-35
DOI: 10.1145/3834764 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 22.08.2026. Verfasst von Chaohao Yuan und 8 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 210 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Damo Academy (Hupan Laboratory) through Damo Academy (Hupan Laboratory) Innovative Research Program, Research Grants Council of the Hong Kong Special Administr…, Shenzhen Science and Technology Innovation Commission, Shenzhen Ubiquitous Data Enabling Key Lab.
Abstract (Originalsprache)
Graph Transformers (GTs) have demonstrated a strong capability in modeling graph structures by addressing the intrinsic limitations of graph neural networks (GNNs), such as over-smoothing and over-squashing. Recent studies have proposed diverse architectures, enhanced explainability, and practical applications for Graph Transformers. In light of these rapid developments, we conduct a comprehensive review of Graph Transformers, covering aspects such as their architectures, theoretical foundations, and applications. In this survey, we first categorize the architecture of Graph Transformers according to their strategies for processing structural information, including graph tokenization, positional encoding, structure-aware attention, and model ensemble. Then, from the theoretical perspective, we examine the expressivity of Graph Transformers in various discussed architectures and contrast them with other advanced graph learning algorithms to discover their connections. For applications, we organize the literature around four graph organization forms, from relational, geometric, dynamic to heterogeneous. A Practical Guidance table then maps architectural components to these graph forms by adoption frequency, so practitioners can narrow down which design families to consider for a given input structure. Lastly, we will discuss the current challenges and prospective directions in Graph Transformers for potential future research.
Förderung
- Damo Academy (Hupan Laboratory) through Damo Academy (Hupan Laboratory) Innovative Research Program, Research Grants Council of the Hong Kong Special Administr…
- Shenzhen Science and Technology Innovation Commission
- Shenzhen Ubiquitous Data Enabling Key Lab
- Tsinghua University SIGS Start-up fund
Zitieren
APA
Yuan, C., Zhao, K., Kuruoglu, E., Wang, L., Xu, T., Huang, W., Zhao, D., Cheng, H., & Rong, Y. (2026). A Survey of Graph Transformers: Architectures, Theories and Applications. ACM Computing Surveys, 58(15), 1-35. https://doi.org/10.1145/3834764
Vancouver
Yuan C, Zhao K, Kuruoglu E, Wang L, Xu T, Huang W, et al. A Survey of Graph Transformers: Architectures, Theories and Applications. ACM Computing Surveys. 2026;58(15):1-35. doi:10.1145/3834764
BibTeX
@article{Yuan2026,
author = {Yuan, Chaohao and Zhao, Kangfei and Kuruoglu, Ercan and Wang, Liang and Xu, Tingyang and Huang, Wenbing and Zhao, Deli and Cheng, Hong and Rong, Yu},
title = {A Survey of Graph Transformers: Architectures, Theories and Applications},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {15},
pages = {1--35},
doi = {10.1145/3834764}
}
EUVIMED