Disentangled Network Alignment with Matching Explainability
Disentangled Network Alignment with Matching Explainability
复制标题
DOI：
10.1109/infocom.2019.8737411
复制
发表时间：
2019-04
期刊：
影响因子：
--
通讯作者：
Fan Zhou;Zijing Wen;Goce Trajcevski;Kunpeng Zhang;Ting Zhong;Fang Liu
中科院分区：
文献类型：
--
作者：
Fan Zhou;Zijing Wen;Goce Trajcevski;Kunpeng Zhang;Ting Zhong;Fang Liu
网络对齐(NA)是许多应用领域的一个基本问题--从社会网络，到生物学和通信，再到神经科学。主要目标是确定跨多个网络的公共节点和最相似的连接(分别为图表)。现有的许多努力都集中在通过利用锚节点之间的成对相似性来利用各种特征和优化网络映射函数来实现高效的锚节点链接。尽管最近取得了进展，但仍然存在两种挑战：(1)纠缠节点嵌入，这是由于NA的目标相互矛盾：将近端节点以封闭的形式嵌入单个网络中表示，而不是在跨网络映射节点时区分它们；(2)缺乏关于节点匹配和比对的可解释性，这对于理解预测任务是必不可少的。我们提出了一种新的基于匹配技术的异质网络环境下NA的解决方案--d-NAME(Disentanged Network Align With Match Explainability)，该匹配技术以解缠和忠实的方式嵌入节点。NA任务被描述为一个对抗性优化问题，该问题在局部学习锚节点周围的邻近度保持模型的同时，仍然具有区分性。我们还介绍了一种用稳健统计理论来解释我们的半监督模型的方法，通过跟踪每个锚节点的重要性及其对NA性能的解释。这可扩展到许多其他NA方法，因为它提供了模型可解释性。在几个公开数据集上进行的实验表明，d NAME在网络对齐精度和节点匹配排名方面都优于最新的方法。
Network alignment (NA) is a fundamental problem in many application domains – from social networks, through biology and communications, to neuroscience. The main objective is to identify common nodes and most similar connections across multiple networks (resp. graphs). Many of the existing efforts focus on efficient anchor node linkage by leveraging various features and optimizing network mapping functions with the pairwise similarity between anchor nodes. Despite the recent advances, there still exist two kinds of challenges: (1) entangled node embeddings, arising from the contradictory goals of NA: embedding proximal nodes in a closed form for representation in a single network vs. discriminating among them when mapping the nodes across networks; and (2) lack of interpretability about the node matching and alignment, essential for understanding prediction tasks. We propose d NAME (disentangled Network Alignment with Matching Explainability) – a novel solution for NA in heterogeneous networks settings, based on a matching technique that embeds nodes in a disentangled and faithful manner. The NA task is cast as an adversarial optimization problem which learns a proximity-preserving model locally around the anchor nodes, while still being discriminative. We also introduce a method to explain our semi-supervised model with the theory of robust statistics, by tracing the importance of each anchor node and its explanations on the NA performance. This is extensible to many other NA methods, as it provides model interpretability. Experiments conducted on several public datasets show that d NAME outperforms the state-of-the-art methods in terms of both network alignment precision and node matching ranking.