CORE: Data Augmentation for Link Prediction via Information Bottleneck
ACM Transactions on Knowledge Discovery from Data · 30.04.2026 · 20 (3) · 1-28
DOI: 10.1145/3789200 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 07.03.2026. Verfasst von Kaiwen Dong und 2 weiteren Autor:innen. Die Arbeit nennt 81 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Link Prediction (LP) is a fundamental task in graph representation learning, with numerous applications in diverse domains. However, the generalizability of LP models is often compromised due to the presence of noisy or spurious information in graphs and the inherent incompleteness of graph data. To address these challenges, we draw inspiration from the Information Bottleneck principle and propose a novel data augmentation method, COmplete and REduce (CORE) to learn compact and predictive augmentations for LP models. In particular, CORE aims to recover missing edges in graphs while simultaneously removing noise from the graph structures, thereby enhancing the model’s robustness and performance. Extensive experiments on multiple benchmark datasets demonstrate the applicability and superiority of CORE over state-of-the-art methods, showcasing its potential as a leading approach for robust LP in graph representation learning.
Förderung
- National Science Foundation
Zitieren
APA
Dong, K., Guo, Z., & Chawla, N. V. (2026). CORE: Data Augmentation for Link Prediction via Information Bottleneck. ACM Transactions on Knowledge Discovery from Data, 20(3), 1-28. https://doi.org/10.1145/3789200
Vancouver
Dong K, Guo Z, Chawla NV. CORE: Data Augmentation for Link Prediction via Information Bottleneck. ACM Transactions on Knowledge Discovery from Data. 2026;20(3):1-28. doi:10.1145/3789200
BibTeX
@article{Dong2026,
author = {Dong, Kaiwen and Guo, Zhichun and Chawla, Nitesh V.},
title = {CORE: Data Augmentation for Link Prediction via Information Bottleneck},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2026},
volume = {20},
number = {3},
pages = {1--28},
doi = {10.1145/3789200}
}
EUVIMED