Research on Link Prediction Algorithms Based on Multichannel Structure Modelling  

作　　者：Gege Li Lin Zhou Zhonglin Ye Haixing Zhao 

机构地区：[1]College of Computer,Qinghai Normal University,Xining,Qinghai,China [2]The State Key Laboratory of Tibetan Intelligent Information Processing and Application,Xining,Qinghai,China [3]Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province,Xining,Qinghai,China [4]Key Laboratory of Tibetan Information Processing,Ministry of Education,Xining,Qinghai,China

出　　处：《国际计算机前沿大会会议论文集》2023年第2期269-284,共16页International Conference of Pioneering Computer Scientists, Engineers and Educators（ICPCSEE）

基　　金：This article was supported by the National Key Research and Development Program of China(No.2020YFC1523300);the Innovation Platform Construction Project of Qinghai Province(2022-ZJ-T02).

摘　　要：Today’s link prediction methods are based on the network structure using a single-channel approach for prediction,and there is a lack of link prediction algorithms constructed from a multichannel approach,which makes the features monotonous and noncomplementary.To address this problem,this paper proposes a link prediction algorithm based on multichannel structure modelling(MCLP).First,the network is sampled three times to construct its three subgraph structures.Second,the node representation vectors of the network are learned separately for each subgraph on a single channel.Then,the three node representation vectors are combined,and the similarity matrix is calculated for the combined vectors.Finally,the performance of the MCLP algorithm is evaluated by calculating the AUC using the similarity matrix and conducting multiple experiments on three citation network datasets.The experimental results show that the proposed link prediction algorithm has an AUC of 98.92%,which is better than the performance of the 24 link prediction comparison algorithms used in this paper.The experimental results sufficiently prove that the MCLP algorithm can effectively extract the relationships between network nodes,and confirm its effectiveness and feasibility.

关 键 词：Link Prediction Subgraph Sampling Matrix Factorization Similarity Matrix MULTICHANNEL 

分 类 号：TN9[电子电信—信息与通信工程]