IGT4ETH: An Isotropic Pre-trained Graph Transformer for Ethereum Account Classification
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (28) · 23631-23639
DOI: 10.1609/aaai.v40i28.39536 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ao Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Pre-trained language models (PLMs) have shown strong potential in Ethereum account modeling and fraud detection. However, existing approaches often overlook the graph-structured nature of transaction networks. In addition, they struggle with the long-tail distribution of account activity, resulting in anisotropic embedding spaces and poor representation quality for low-frequency accounts. In this paper, we present IGT4ETH, a pre-trained Graph Transformer with an isotropy-enhanced post-processing, which explicitly models transaction topologies and mitigates representational anisotropy for Ethereum account classification. IGT4ETH improves structural representation by incorporating structural centrality and role embeddings into an Edge-augmented Graph Transformer, effectively capturing both topological and interaction patterns in transaction graphs. To further mitigate embedding anisotropy, we systematically evaluate various post-processing techniques. Among them, we adopt the Conceptor Negation (CN) method to softly suppress latent features dominated by high-frequency words via matrix conceptors, alongside a modified Focal-InfoNCE loss to enhance directional uniformity and representation balance. Extensive experiments on four real-world Ethereum account classification tasks, including phishing, exchange, mining, and ICO-wallet classification, demonstrate that IGT4ETH consistently outperforms state-of-the-art PLM-based baselines in terms of classification performance.
Zitieren
APA
Liu, A., Zhang, Y., Wang, Y., & Duan, Q. (2026). IGT4ETH: An Isotropic Pre-trained Graph Transformer for Ethereum Account Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 40(28), 23631-23639. https://doi.org/10.1609/aaai.v40i28.39536
Vancouver
Liu A, Zhang Y, Wang Y, Duan Q. IGT4ETH: An Isotropic Pre-trained Graph Transformer for Ethereum Account Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(28):23631-23639. doi:10.1609/aaai.v40i28.39536
BibTeX
@article{Liu2026,
author = {Liu, Ao and Zhang, Yanmei and Wang, Youwei and Duan, Qiang},
title = {IGT4ETH: An Isotropic Pre-trained Graph Transformer for Ethereum Account Classification},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {28},
pages = {23631--23639},
doi = {10.1609/aaai.v40i28.39536}
}
EUVIMED