| 基于邻节点和关系模型优化的网络表示学习 |
| |
| 引用本文： | 冶忠林, 赵海兴, 张科, 朱宇, 肖玉芝. 基于邻节点和关系模型优化的网络表示学习[J]. 计算机研究与发展, 2019, 56(12): 2562-2577. DOI: 10.7544/issn1000-1239.2019.20180566 |
| |
| 作者姓名： | 冶忠林 赵海兴 张科 朱宇 肖玉芝 |
| |
| 作者单位： | 1.1(青海师范大学计算机学院 西宁 810008);2.2(陕西师范大学计算机科学学院 西安 710119);3.3(藏文信息处理教育部重点实验室(青海师范大学) 西宁 810008) (zhonglin_ye@foxmail.com) |
| |
| 基金项目： | 国家自然科学基金;国家自然科学基金;国家自然科学基金;长江学者;创新研究团队项目;青海省自然科学基金;中央高校基本科研业务费专项 |
| |
| 摘 要： | 网络表示学习旨在于将网络的拓扑结构、节点内容和其他信息嵌入到低维度的向量空间中，从而为网络数据挖掘、链路预测和推荐系统提供一种有效的工具.然而，现有的基于神经网络的表示学习算法即忽略了上下文节点的位置信息，又忽略了节点与文本之间的语义关联.因此，基于以上2点，提出了一种新颖的基于邻节点和关系模型优化的网络表示学习算法(network representation learning algorithm using the optimizations of neighboring vertices and relation model， NRNR).首先，该算法首次采用当前节点的邻居节点优化网络表示学习模型，使得上下文窗口中节点的位置信息被嵌入到网络表示中；其次，该算法首次引入知识表示学习中的关系模型建模节点之间的结构特征，使得节点之间的文本内容以关系约束的形式嵌入到网络表示中；再次，NRNR提出了一种可行且有效的网络表示联合学习框架，将上述2种目标融入到一个统一的优化目标函数中.实验结果表明：NRNR算法在网络节点分类任务中优于各类对比算法，在网络可视化中，NRNR算法学习得到的网络表示展现出了明显的聚类边界.
|
| 关 键 词： | 网络表示学习 网络嵌入 网络表示 节点向量 网络特征学习 |
Network Representation Learning Using the Optimizations of Neighboring Vertices and Relation Model |
| |
| Ye Zhonglin, Zhao Haixing, Zhang Ke, Zhu Yu, Xiao Yuzhi. Network Representation Learning Using the Optimizations of Neighboring Vertices and Relation Model[J]. Journal of Computer Research and Development, 2019, 56(12): 2562-2577. DOI: 10.7544/issn1000-1239.2019.20180566 |
| |
| Authors: | Ye Zhonglin Zhao Haixing Zhang Ke Zhu Yu Xiao Yuzhi |
| |
| Affiliation: | 1.1(College of Computer, Qinghai Normal University, Xining 810008);2.2(College of Computer Science, Shaanxi Normal University, Xi’an 710119);3.3(Key Laboratory of Tibetan Information Processing (Qinghai Normal University), Ministry of Education, Xining 810008) |
| |
| Abstract: | Network representation learning aims at embedding the network topology structures, vertex contents and other information of networks into the low-dimensional vector space, which thus provides an effective tool for network data mining, link prediction and recommendation system etc. However, the existing learning algorithms based on neural networks neglect the location information of the context vertices. Meanwhile, this kind of algorithms ignore the semantic associations between vertices and texts. Therefore, this paper proposes a novel network representation learning algorithm using the optimizations of neighboring vertices and relation model (NRNR). NRNR first uses the neighboring vertices to optimize the learning procedure, consequently, the location information of the vertices in the context windows is embedded into the network representations. In addition, NRNR first introduces the relational modeling from knowledge representation learning to learn the structure features of the networks, and the text contents between vertices are thus embedded into the network representations with the form of relational constraints. Moreover, NRNR proposes a feasible and effective network representation joint learning framework, which integrates the above two goals into a unified optimization objective function. The experimental results show that the proposed NRNR algorithm is superior to all kinds of baseline algorithms applied to the network node classification tasks in this paper. In network visualization tasks, the network representations obtained by NRNR algorithm show a distinct clustering boundary. |
| |
| Keywords: | network representation learning network embedding network representation vertex vector network feature learning |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机研究与发展》浏览原始摘要信息 |
|
点击此处可从《计算机研究与发展》下载全文 |
|
