The Node-Similarity Distribution of Complex Networks and Its Applications in Link Prediction (Extended Abstract)

Cunlai Pu, Jie Li, Jian Wang, Tony Q.S. Quek

研究成果: Conference contribution

摘要

Node-similarity distributions not only characterize different types of complex networks, but also offer insights in the structural predictability of complex networks, and even facilitate prediction tasks in complex networks. By means of the generating function, we propose a framework to calculate the common neighbor based similarity (CNS) distributions, offering theoretical results of similarity distributions of various complex networks. Furthermore, we apply node-similarity distributions to link prediction, a key task in network analysis. Specifically, by deriving analytical solutions for two metrics: i) precision and ii) area under the receiver operating characteristic curve (AUC), we give theoretical evaluation of link prediction. Also, by analyzing i) the expected prediction accuracy of similarity scores and ii) optimal prediction priority of unconnected node pairs, we optimize link prediction with similarity distributions. Simulation results confirm our findings and also validate the proposed methods for evaluating and optimizing link prediction.

原文English
主出版物標題Proceedings - 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023
發行者IEEE Computer Society
頁面3899-3900
頁數2
ISBN(電子)9798350322279
DOIs
出版狀態Published - 2023
事件39th IEEE International Conference on Data Engineering, ICDE 2023 - Anaheim, United States
持續時間: 2023 4月 32023 4月 7

出版系列

名字Proceedings - International Conference on Data Engineering
2023-April
ISSN(列印)1084-4627

Conference

Conference39th IEEE International Conference on Data Engineering, ICDE 2023
國家/地區United States
城市Anaheim
期間23-04-0323-04-07

All Science Journal Classification (ASJC) codes

  • 軟體
  • 訊號處理
  • 資訊系統

指紋

深入研究「The Node-Similarity Distribution of Complex Networks and Its Applications in Link Prediction (Extended Abstract)」主題。共同形成了獨特的指紋。

引用此