Know Your Neighbors: Subgraph Importance Sampling for Heterophilic Graph Active Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (33) · 27630-27638
DOI: 10.1609/aaai.v40i33.39983 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wenjie Yang und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Graph neural networks (GNNs) have demonstrated strong performance in various graph mining tasks but rely heavily on extensively labeled nodes. To improve training efficiency, graph active learning (GAL) has emerged as a solution for selecting the most informative nodes for labeling. However, existing GAL methods are primarily designed for homophilic graphs, where nodes with the same labels are more likely to be connected. In this work, we systematically study active learning on heterophilic graphs, a setting that has received limited attention. Surprisingly, we observe that existing GAL methods fail to consistently outperform random sampling on heterophilic graphs. Through an in-depth investigation, we reveal that these methods implicitly assume homophily even on heterophilic graphs, leading to suboptimal performance. To address this issue, we introduce the principle of "Know Your Neighbors" and propose an active learning algorithm KyN specifically for heterophilic graphs. The core idea of KyN is to provide GNNs with accurate estimations of homophily distribution by labeling nodes together with their neighbors. We implement KyN based on subgraph sampling with probabilities proportional to l1 Lewis weights, which is supported by solid theoretical guarantees. Extensive experiments on diverse real-world datasets, including a large heterophilic graph with over 2 million nodes, demonstrate the effectiveness and scalability of KyN.
Zitieren
APA
Yang, W., Zhang, S., Ye, C., Guo, J., Xu, T., & Huang, Z. (2026). Know Your Neighbors: Subgraph Importance Sampling for Heterophilic Graph Active Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(33), 27630-27638. https://doi.org/10.1609/aaai.v40i33.39983
Vancouver
Yang W, Zhang S, Ye C, Guo J, Xu T, Huang Z. Know Your Neighbors: Subgraph Importance Sampling for Heterophilic Graph Active Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(33):27630-27638. doi:10.1609/aaai.v40i33.39983
BibTeX
@article{Yang2026,
author = {Yang, Wenjie and Zhang, Shengzhong and Ye, Chen and Guo, Jiaxing and Xu, Tongshan and Huang, Zengfeng},
title = {Know Your Neighbors: Subgraph Importance Sampling for Heterophilic Graph Active Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {33},
pages = {27630--27638},
doi = {10.1609/aaai.v40i33.39983}
}
EUVIMED