首页|Researchers from Xihua University Provide Details of New Studies and Findings in the Area of Intelligent Systems (Bi-dne: Bilayer Evolutionary Pattern Preserved Embedding for Dynamic Networks)
Researchers from Xihua University Provide Details of New Studies and Findings in the Area of Intelligent Systems (Bi-dne: Bilayer Evolutionary Pattern Preserved Embedding for Dynamic Networks)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ma chine Learning - Intelligent Systems. According to news reporting originating fr om Chengdu,People's Republic of China,by NewsRx correspondents,research state d,"Network embedding is a technique used to generate low-dimensional vectors re presenting each node in a network while maintaining the original topology and pr operties of the network. This technology enables a wide range of learning tasks,including node classification and link prediction." Funders for this research include National Natural Science Foundation of China ( NSFC),Science and Technology Program of Sichuan Province,National Natural Scie nce Foundation of China (NSFC),Foundation of Cyberspace Security Key Laboratory of Sichuan Higher Education Institutions. Our news editors obtained a quote from the research from Xihua University,"Howe ver,the current landscape of network embedding approaches predominantly revolve s around static networks,neglecting the dynamic nature that characterizes real social networks. Dynamics at both the micro- and macrolevels are fundamental dri vers of network evolution. Microlevel dynamics provide a detailed account of the network topology formation process,while macrolevel dynamics reveal the evolut ionary trends of the network. Despite recent dynamic network embedding efforts,a few approaches accurately capture the evolution patterns of nodes at the micro level or effectively preserve the crucial dynamics of both layers. Our study int roduces a novel method for embedding networks,i.e.,bilayer evolutionary patter n-preserving embedding for dynamic networks (Bi-DNE),that preserves the evoluti onary patterns at both the microand macrolevels. The model utilizes strengthen ed triadic closure to represent the network structure formation process at the m icrolevel,while a dynamic equation constrains the network structure to adhere t o the densification power-law evolution pattern at the macrolevel. The proposed Bi-DNE model exhibits significant performance improvements across a range of tas ks,including link prediction,reconstruction,and temporal link analysis. These improvements are demonstrated through comprehensive experiments carried out on both simulated and real-world dynamic network datasets. The consistently superio r results to those of the state-of-the-art methods provide empirical evidence fo r the effectiveness of Bi-DNE in capturing complex evolutionary patterns and lea rning high-quality node representations. These findings validate the methodologi cal innovations presented in this work and mark valuable progress in the emergin g field of dynamic network representation learning."
ChengduPeople's Republic of ChinaAsi aIntelligent SystemsMachine LearningXihua University
NETL
NSTL
