期刊
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
卷 36, 期 12, 页码 7895-7924出版社
WILEY-HINDAWI
DOI: 10.1002/int.22613
关键词
adversarial learning; graph neural networks; matching uncertainty; model interpretability; network alignment
资金
- National Natural Science Foundation of China [62072077]
- National Science Foundation SWIFT [2030249]
- National Key R&D Program of China [2019YFB1406202]
- Div Of Electrical, Commun & Cyber Sys
- Directorate For Engineering [2030249] Funding Source: National Science Foundation
This study proposes a novel framework UANA, which embeds nodes as Gaussian distributions instead of point vectors to capture uncertainty and address limitations in existing works. An adversarial learning paradigm is introduced to tackle the P2P matching constraint. Interpretability methods are included to explain aligning results and the effects of individual training samples on NA performance.
Network alignment (NA) aims to link common nodes across multiple networks and is an essential task in many graph mining applications. Despite the progress achieved by many recent works, several fundamental limitations have eluded the proper cohesive way of addressing, including matching confusion, lack of the formal treatment of uncertainty, and Point-to-Point (P2P) constraint. This study proposes a novel framework UANA (Uncertainty-Aware Network Alignment) to tackle the limitations of the existing works. By embedding nodes as Gaussian distributions rather than point vectors, UANA enables to capture the uncertainty of a node representation, while being able to discriminate the anchor nodes from the potentially confusing neighbors. We address the P2P matching constraint by introducing an adversarial learning paradigm, which relaxes the exact matching assumption during training with an across-domain generative procedure to reduce the matching errors on testing nodes. In the end, interpretability methods are included to explain the aligning results made by our UANA based on the robust statistics, which enables the explanation of the effect of individual training sample on the NA performance without the need of retraining the model. Extensive experiments conducted on real-world data sets demonstrate that UANA significantly outperforms existing state-of-the-art baselines while providing explainable results.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据