当前位置: X-MOL 学术Inf. Process. Manag. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
HCNA: Hyperbolic Contrastive Learning Framework for Self-Supervised Network Alignment
Information Processing & Management ( IF 7.4 ) Pub Date : 2022-07-22 , DOI: 10.1016/j.ipm.2022.103021
Shruti Saxena , Roshni Chakraborty , Joydeep Chandra

Network alignment, or identifying the same entities (anchors) across multiple networks, has significant applications across diverse fields. Unsupervised approaches for network alignment, though popular, strictly assume that the anchor nodes’ structure and attributes remain consistent across different networks. However, in practice, strictly adhering to these constraints makes it difficult to deal with networks with high variance in the structural characteristics and inherent structural noises like missing nodes and edges, resulting in poor generalization. In order to handle these shortcomings, we propose HCNA: Hyperbolic Contrastive Learning Framework for Self-Supervised Network Alignment, a novel self-supervised contrastive learning model which learns from the multiple augmented views of each network, thereby making HCNA robust to the inherent multi-network characteristics. Furthermore, we propose multi-order hyperbolic graph convolution networks to generate node embedding for each network which can handle the hierarchical structure of networks. The main objective of HCNA is to obtain structure-preserving embeddings that are also robust to noises and variations for better alignment results. The major novelty lies in generating augmented multiple graph views for contrastive learning that are driven by real world network dynamics. Rigorous investigations on 4 real datasets show that HCNA consistently outperforms the baselines by at least 184% in terms of accuracy score. Furthermore, HCNA is also more resilient to structural and attributes noises, as evidenced by its adaptivity analysis on adversarial conditions.



中文翻译:

HCNA:用于自监督网络对齐的双曲对比学习框架

网络对齐或跨多个网络识别相同实体(锚点)在不同领域具有重要应用。网络对齐的无监督方法虽然很流行,但严格假设锚节点的结构和属性在不同的网络中保持一致。然而,在实践中,严格遵守这些约束使得难以处理结构特征具有高方差和固有结构噪声(如缺失节点和边缘)的网络,导致泛化性差。为了解决这些缺点,我们提出了 HCNA:Hyperbolic Contrastive Learning Framework for Self-Supervised Network Alignment,一种新颖的自我监督对比学习模型,它从每个网络的多个增强视图中学习,从而使 HCNA 对固有的多网络特征具有鲁棒性。此外,我们提出了多阶双曲图卷积网络,为每个网络生成节点嵌入,可以处理网络的层次结构。HCNA 的主要目标是获得对噪声和变化也具有鲁棒性的结构保持嵌入,以获得更好的对齐结果。主要的新颖之处在于为由现实世界网络动态驱动的对比学习生成增强的多个图形视图。对 4 个真实数据集的严格调查表明,HCNA 始终优于基线至少184%在准确率方面。此外,HCNA 对结构和属性噪声也更具弹性,其对对抗条件的适应性分析证明了这一点。

更新日期:2022-07-22
down
wechat
bug