Gradual Domain Adaptation for Graph Learning
ACM Transactions on Intelligent Systems and Technology · 31.10.2026 · 17 (5) · 1-45
DOI: 10.1145/3815185 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 23.07.2026. Verfasst von Pui Ieng Lei und 5 weiteren Autor:innen. Die Arbeit nennt 105 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Development Fund and the University of Macau.
Abstract (Originalsprache)
Existing machine learning literature lacks graph-based domain adaptation techniques capable of handling large distribution shifts, primarily due to the difficulty in simulating a coherent evolutionary path from source to target graph. To meet this challenge, we present a graph gradual domain adaptation (GGDA) framework, which constructs a compact domain sequence that minimizes information loss during adaptation. Our approach starts with an efficient generation of knowledge-preserving intermediate graphs over the Fused Gromov-Wasserstein (FGW) metric. A GGDA domain sequence is then constructed upon this bridging data pool through a novel vertex-based progression, which involves selecting “close” vertices and performing adaptive domain advancement to enhance inter-domain transferability. Theoretically, our framework provides implementable upper and lower bounds for the intractable inter-domain Wasserstein distance, \(W_{p}(\mu_{t},\mu_{t+1})\) , enabling its flexible adjustment for optimal domain formation. Extensive experiments across diverse transfer scenarios demonstrate the superior performance of our GGDA framework. Our code is available at https://github.com/Louisa-LPI/GGDA .
Förderung
- Science and Technology Development Fund and the University of Macau
Zitieren
APA
Lei, P. I., Chen, X., Sheng, Y., Liu, Y., Gong, Z., & Yang, Q. (2026). Gradual Domain Adaptation for Graph Learning. ACM Transactions on Intelligent Systems and Technology, 17(5), 1-45. https://doi.org/10.1145/3815185
Vancouver
Lei PI, Chen X, Sheng Y, Liu Y, Gong Z, Yang Q. Gradual Domain Adaptation for Graph Learning. ACM Transactions on Intelligent Systems and Technology. 2026;17(5):1-45. doi:10.1145/3815185
BibTeX
@article{Lei2026,
author = {Lei, Pui Ieng and Chen, Ximing and Sheng, Yijun and Liu, Yanyan and Gong, Zhiguo and Yang, Qiang},
title = {Gradual Domain Adaptation for Graph Learning},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2026},
volume = {17},
number = {5},
pages = {1--45},
doi = {10.1145/3815185}
}
EUVIMED