Collective Link Prediction Oriented Network Embedding with Hierarchical Graph Attention
Collective Link Prediction Oriented Network Embedding with Hierarchical Graph Attention
复制标题
DOI：
10.1145/3357384.3357990
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Yizhu Jiao;Yun Xiong;Jiawei Zhang;Yangyong Zhu
中科院分区：
文献类型：
--
作者：
Yizhu Jiao;Yun Xiong;Jiawei Zhang;Yangyong Zhu
为了享受更多的社交网络服务，现在的用户通常同时参与多个在线网站。一致的社交网络提供了更多的信息，以缓解数据不足的问题。在本文中，我们针对集体链接预测问题，旨在预测跨多个对齐的社交网络的网络内社会链接和网络间锚链接。这不是一项容易的任务，主要的挑战涉及到网络特征差异问题和待预测的社会链接和锚链接的不同指向性属性。为了解决这个问题，我们提出了一个面向应用的网络嵌入框架——基于层次图注意力的网络嵌入（HGANE），用于有向对齐网络上的集体链接预测。与传统的一般网络嵌入模型不同，HGANE有效地考虑了集体链路预测任务目标。它通过聚合来自网络内邻居（通过社会链接连接）和网络间伙伴（通过锚链接连接）的信息来学习节点的表示。此外，我们还分别针对网络内邻居和网络间伙伴引入了层次图注意机制，有效地解决了网络特征差异和链路指向性挑战。在现实世界的对齐网络数据集上进行了大量的实验，以证明我们的模型在解决集体链路预测问题方面优于最先进的基线方法。
To enjoy more social network services, users nowadays are usually involved in multiple online sites at the same time. Aligned social networks provide more information to alleviate the problem of data insufficiency. In this paper, we target on the collective link prediction problem and aim to predict both the intra-network social links as well as the inter-network anchor links across multiple aligned social networks. It is not an easy task, and the major challenges involve the network characteristic difference problem and different directivity properties of the social and anchor links to be predicted. To address the problem, we propose an application oriented network embedding framework, Hierarchical Graph Attention based Network Embedding (HGANE), for collective link prediction over directed aligned networks. Very different from the conventional general network embedding models, HGANE effectively incorporates the collective link prediction task objectives into consideration. It learns the representations of nodes by aggregating information from both the intra-network neighbors (connected by social links) and inter-network partners (connected by anchor links). What's more, we introduce a hierarchical graph attention mechanism for the intra-network neighbors and inter-network partners respectively, which resolves the network characteristic differences and the link directivity challenges effectively. Extensive experiments have been conducted on real-world aligned networks datasets to demonstrate that our model outperformed the state-of-the-art baseline methods in addressing the collective link prediction problem by a large margin.