Self-Supervised Aggregation Framework for Text-Attributed Heterogeneous Graphs Representation
IEEE Transactions on Knowledge and Data Engineering · 2026-07 · 38 (7) · 4694-4706
DOI: 10.1109/tkde.2026.3683100 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-07. Verfasst von Fei Teng und 4 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Sichuan Province Outstanding Young Scientist Fund, Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China.
Abstract (Originalsprache)
Text-Attributed Heterogeneous Graphs (TAHGs) integrate topological relationships with rich textual node attributes, offering expressive representations for complex multi-faceted data. While recent methods jointly leverage textual and structural information, they still face two critical limitations: (i) existing approaches are constrained to neighborhood modeling, failing to capture semantic dependencies in higher-order topologies; (ii) current techniques exhibit inadequate unified alignment strategies, limiting dynamic interaction between cross modalities. To address these challenges, we propose SATH, a self-supervised information aggregation model for TAHGs, designed to effectively leverage textual and structural information within TAHGs. SATH aggregates higher-order neighbor textual attributes through comparative learning, and dynamically aligns these attributes to higher-order topologies through a unified strategy. This approach integrates both types of information effectively, enhancing the expressiveness and discriminative capability of the learned node representations in downstream tasks. Extensive experiments on real-world datasets demonstrate that SATH significantly outperforms baseline models while eliminating the need for manual meta-path design or text feature concatenation. It also improves efficiency and scalability on large-scale TAHGs, achieving superior representation quality in TAHG-based tasks.
Förderung
- National Natural Science Foundation of China
- Sichuan Province Outstanding Young Scientist Fund
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China
Zitieren
APA
Teng, F., Xiao, Q., Li, X., Ye, X., & Li, Q. (2026). Self-Supervised Aggregation Framework for Text-Attributed Heterogeneous Graphs Representation. IEEE Transactions on Knowledge and Data Engineering, 38(7), 4694-4706. https://doi.org/10.1109/tkde.2026.3683100
Vancouver
Teng F, Xiao Q, Li X, Ye X, Li Q. Self-Supervised Aggregation Framework for Text-Attributed Heterogeneous Graphs Representation. IEEE Transactions on Knowledge and Data Engineering. 2026;38(7):4694-4706. doi:10.1109/tkde.2026.3683100
BibTeX
@article{Teng2026,
author = {Teng, Fei and Xiao, Quyan and Li, Xingwang and Ye, Xiaoqing and Li, Qian},
title = {Self-Supervised Aggregation Framework for Text-Attributed Heterogeneous Graphs Representation},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2026},
volume = {38},
number = {7},
pages = {4694--4706},
doi = {10.1109/tkde.2026.3683100}
}
EUVIMED