Heterogeneous Information Networks Embedding Based on Multiple Meta-Graph Fusion
-
摘要: 基于元结构(如元路径或元图)的网络嵌入方法,能够有效地利用异构网络结构.但与元路径相比,元图能够捕获更加复杂的结构信息,更能提升异构信息网中相似节点匹配的准确性.然而,现有的基于元图的嵌入方法具有如下局限:大多由专家指定元图类型,在大型复杂网络的应用环境中并不适用;虽然融合了多个元图进行嵌入,但并未考虑元图权重的差异性;部分模型利用用户的期望语义关系生成可以保留特定语义的元图组合,但这类模型过分依赖元图选择和用于监督学习的样本,缺乏通用性.基于此,提出一种多元图融合的异构网络嵌入方法,该方法包括2部分:第1部分是元图发现,目的是挖掘代表当前网络结构和语义特征的重要元图;第2部分是基于多元图融合的节点嵌入,主要内容是提出了一种基于元图的通用节点相似度度量方法,同时利用神经网络嵌入节点的元图特征.实验结果表明,与其他网络嵌入方法相比,提出的方法具有较高的准确性和效率.Abstract: Network embedding methods based on meta-structures (such as meta-path or meta-graph) can effectively utilize heterogeneous network structures. Compared with the meta-path, the meta-graph can capture more complex structural information and help improve the accuracy of similar node matching in heterogeneous information networks. However, the existing meta-graph-based embedding method typically has the following limitations: 1)Most of the meta-graph types are specified by experts, and are not applicable in the application environment of large complex networks; 2)Although multiple meta-graphs are integrated for embedding, the weights of meta-graphs are not considered; 3)Some models use the users expected semantic relationship to generate a combination of meta-graphs that can preserve specific semantics, but such models are over-reliant on meta-pattern selection and samples used to supervise learning, lacking versatility. Based on this, this paper proposes a heterogeneous network embedding method based on multiple meta-graph fusion. The method includes two parts. The first part is graph discovery. The purpose of graph discovery is to mine important meta-graphs representing the current network structure and semantic features. The second part is node embedding based on multiple meta graph fusion. The main content is to propose a general graph similarity measure method based on meta-graphs, and use the neural network to embed the meta-graph features of nodes. Experimental results show that the proposed method has higher accuracy and efficiency compared with other network embedding methods.
-
Keywords:
- heterogeneous information networks /
- network embedding /
- meta-graph /
- meta-path /
- fusion
-
-
期刊类型引用(5)
1. 苏晓萍,查英华,曲鸿博. 一种异质图的Lorentz嵌入模型. 电子科技大学学报. 2023(01): 146-153 . 百度学术
2. 王宏琳,杨丹,聂铁铮,寇月. 自注意力机制的属性异构信息网络嵌入的商品推荐. 计算机研究与发展. 2022(07): 1509-1521 . 本站查看
3. 花豹,周彬,顾星海,鲍劲松. 基于图神经网络的工艺表格语义相似性度量. 计算机集成制造系统. 2022(12): 3805-3821 . 百度学术
4. 马扬,刘泽一,梁星星,程光权,阳方杰,成清,刘忠. 基于病毒传播网络的基因序列表示学习. 计算机研究与发展. 2021(08): 1642-1654 . 本站查看
5. 蒋璐,陈云伟. 多节点多关系的混合网络社团划分研究综述. 图书情报工作. 2021(19): 142-150 . 百度学术
其他类型引用(4)
计量
- 文章访问数: 1034
- HTML全文浏览量: 5
- PDF下载量: 452
- 被引次数: 9