Author:
Dai Yulong,Shen Qiyou,Xu Xiangqian,Yang Jun
Abstract
Abstract
Most real-world systems consist of a large number of interacting entities of many types. However, most of the current researches on systems are based on the assumption that the type of node or link in the network is unique. In other words, the network is homogeneous, containing the same type of nodes and links. Based on this assumption, differential information between nodes and edges is ignored. This paper firstly introduces the research background, challenges and significance of this research. Secondly, the basic concepts of the model are introduced. Thirdly, a novel type-sensitive LeaderRank algorithm is proposed and combined with distance rule to solve the importance ranking problem of content-associated heterogeneous graph nodes. Finally, the writer influence data set is used for experimental analysis to further prove the validity of the model.
Subject
General Physics and Astronomy
Reference14 articles.
1. Streaming Social Event Detection and Evolution Discovery in Heterogeneous Information Networks;Hao;ACM Transactions on Knowledge Discovery from Data.,2021
2. TOSNet: A Topic-Based Optimal Subnetwork Identification in Academic Networks;Bedru;IEEE Access, Access, IEEE.,2020
3. A Quantitative Study of the Perceived Impact of Social Media Networks on Bahraini Users’ English Language Learning;Jahromi;Teaching English with Technology,2020
4. Attention-Aware Encoder–Decoder Neural Networks for Heterogeneous Graphs of Things;Li;IEEE Transactions on Industrial Informatics, Industrial Informatics. IEEE Transactions on, IEEE Trans Ind Inf.,2021
5. PageRank on inhomogeneous random digraphs;Lee;Stochastic Processes and their Applications,2020