arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1901.07264cs.SI
收藏

Network Together:基于跨网络深度网络嵌入的节点分类

Network Together: Node Classification via Cross network Deep Network Embedding

Xiao Shen, Quanyu Dai, Sitong Mao, Fu-lai Chung, Kup-Sze Choi

摘要:

网络嵌入是一种高效的学习低维节点向量表示的方法,并且可以很好地保留原始网络结构。然而,现有的网络嵌入算法大多是针对单个网络开发的,无法跨网络学习广义特征表示。本文研究了跨网络节点分类问题,旨在利用源网络中丰富的标记信息来帮助对目标网络中未标记的节点进行分类。为了成功地完成这样的任务,应该为跨不同网络的节点学习可转移的特征。为此,提出了一种新的跨网络深度网络嵌入(CDNE)模型,将领域自适应纳入深度网络嵌入,以学习标签区分和网络不变的节点向量表示。一方面,CDNE利用网络结构来捕获网络内节点之间的邻近性,通过映射更强连接的节点以具有更相似的潜在向量表示。另一方面,节点属性和标签被利用来捕获跨不同网络的节点之间的邻近度,这是通过使跨网络的相同标记的节点具有对齐的潜在向量表示来实现的。大量的实验表明,提出的CDNE模型在跨网络节点分类方面明显优于现有的网络嵌入算法。

英文摘要:

Network embedding is a highly effective method to learn low-dimensional node vector representations with original network structures being well preserved. However, existing network embedding algorithms are mostly developed for a single network, which fail to learn generalized feature representations across different networks. In this paper, we study a cross-network node classification problem, which aims at leveraging the abundant labeled information from a source network to help classify the unlabeled nodes in a target network. To succeed in such a task, transferable features should be learned for nodes across different networks. To this end, a novel cross-network deep network embedding (CDNE) model is proposed to incorporate domain adaptation into deep network embedding so as to learn label-discriminative and network-invariant node vector representations. On one hand, CDNE leverages network structures to capture the proximities between nodes within a network, by mapping more strongly connected nodes to have more similar latent vector representations. On the other hand, node attributes and labels are leveraged to capture the proximities between nodes across different networks by making the same labeled nodes across networks have aligned latent vector representations. Extensive experiments have been conducted, demonstrating that the proposed CDNE model significantly outperforms the state-of-the-art network embedding algorithms in cross-network node classification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑