SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15716-15724
DOI: 10.1609/aaai.v40i18.38602 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Junhua Shi und 3 weiteren Autor:innen.
Abstract (Originalsprache)
While Graph Foundation Models (GFMs) have achieved notable progress across diverse tasks recently, their robustness under domain noise, structural perturbations, and adversarial attacks remains largely underexplored. A core limitation lies in inadequate modeling of hierarchical structural semantics, which are intrinsic priors and critical for generalization. In this work, we propose SA^2GFM, a robust GFM framework that enhances domain adaptable representations through Structure Aware Semantic Augmentation. First, to embed hierarchical structural priors, we transform entropy based encoding trees into structure aware textual prompts for feature augmentation. The enriched inputs are processed by a novel self supervised Information Bottleneck mechanism that distills robust and transferable representations through structure guided compression. To mitigate negative transfer in cross domain adaptation, we develop an expert adaptive routing mechanism that integrates a mixture of experts architecture with a null expert design. To enable efficient downstream adaptation, we propose a fine tuning module that optimizes hierarchical structures through joint intra and inter community structure learning. Extensive experiments validate the superiority of SA^2GFM in effectiveness and robustness against random noise and adversarial perturbations on node and graph classification, compared with nine state of the art baselines.
Zitieren
APA
Shi, J., Sun, Q., Yuan, H., & Fu, X. (2026). SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15716-15724. https://doi.org/10.1609/aaai.v40i18.38602
Vancouver
Shi J, Sun Q, Yuan H, Fu X. SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15716-15724. doi:10.1609/aaai.v40i18.38602
BibTeX
@article{Shi2026,
author = {Shi, Junhua and Sun, Qingyun and Yuan, Haonan and Fu, Xingcheng},
title = {SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {18},
pages = {15716--15724},
doi = {10.1609/aaai.v40i18.38602}
}
EUVIMED