Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (30) · 25581-25589
DOI: 10.1609/aaai.v40i30.39754 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yu Song und 7 weiteren Autor:innen.
Abstract (Originalsprache)
Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection and observational constraints, severely limiting the effectiveness of modern graph learning pipelines. While existing Graph Data Augmentation (GDA) methods attempt to refine graph structures for improved downstream performance, they are typically label-dependent, computationally expensive, and inherently transductive, limiting their applicability in practical scenarios. In this work, we present a novel feature-centric graph data augmentation framework that bypasses explicit structure modeling by operating directly in the embedding space. Through a self-supervised inverse masking process, our method captures latent ties between observed and complete graphs, enabling recovery of unobserved structural signals through refined node representations. To enhance robustness under noisy and sparse supervision, we introduce a message regularizer and a bootstrap strategy for effective training and generalization. Evaluated on ten graph datasets spanning multiple domains, our approach, SelfAug, consistently outperforms state-of-the-art methods in both accuracy and efficiency across inductive and cold-start settings, highlighting its potential as a scalable and generalizable solution for real-world graph learning scenarios.
Zitieren
APA
Song, Y., Hua, Z., Xie, Y., Li, B., Liu, J., Long, B., Tang, J., & Liu, H. (2026). Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(30), 25581-25589. https://doi.org/10.1609/aaai.v40i30.39754
Vancouver
Song Y, Hua Z, Xie Y, Li B, Liu J, Long B, et al. Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(30):25581-25589. doi:10.1609/aaai.v40i30.39754
BibTeX
@article{Song2026,
author = {Song, Yu and Hua, Zhigang and Xie, Yan and Li, Bingheng and Liu, Jingzhe and Long, Bo and Tang, Jiliang and Liu, Hui},
title = {Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {30},
pages = {25581--25589},
doi = {10.1609/aaai.v40i30.39754}
}
EUVIMED