期刊
NEUROCOMPUTING
卷 358, 期 -, 页码 1-9出版社
ELSEVIER
DOI: 10.1016/j.neucom.2019.05.038
关键词
Dynamic networks; Attributed networks; Lifelong learning; Network embeddings
资金
- National Key Research Development Program of China [2017YFB0802800]
Network embedding or network representation learning aims at learning a low-dimensional vector for each node in a network. The learned embeddings could advance various learning tasks in the network analysis area. Most existing embedding methods focus on plain and static networks while ignoring network dynamics. However, in real world networks, structure often evolves over time. In addition, many networks contain rich attributes and their attributes are changing over time. Naively applying existing embedding algorithms to each snapshot of dynamic network independently usually leads to unsatisfactory performance. In this paper, we present a Lifelong Dynamic Attributed Network Embedding Framework - LDANE. LDANE has a good mechanism to automatically expand the deep neural networks with the sizes of network growing and preserving what have learned from previous time steps. Furthermore, the proposed framework is carefully designed to flexibly incorporate the topology and attribute of nodes. We perform extensive experiments on both synthetic and real attributed networks to corroborate the significant advantages of the proposed framework compared with the existing state-of-the-art embedding techniques. (C) 2019 Elsevier B.V. All rights reserved.
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