http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Ning Yixin (검색결과 1 건)
- 무료
- 기관 내 무료
- 유료
-
Community detection based on BernNet graph convolutional neural network
Xie Hui,Ning Yixin 한국물리학회 2023 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.83 No.5
As an important part of network analysis, community detection has attracted extensive attention of researchers in various felds. Using Graph Neural Network (GNN) model to solve the problem of community detection is a new direction of community detection research. BernNet is a graph convolutional neural network based on Bernstein polynomial approximation of order K, which can be used to design arbitrary flters, but it is slow because of its quadratic dependence on K. In this paper, a novel algorithm using frst-order Bernstein polynomial is proposed: (i) approximate the defnition of flters, takes the original labels of data as the basis for community division; (ii) defnes the loss function between the labels predicted by the algorithm and the original data labels, (iii) acquires the probability model of node labels predicted by the node characteristic matrix with the smallest loss function through backpropagation. The results of community segmentation are evaluated using Normalized Mutual Information (NMI). Compared with the state-of-the-art methods, the experimental results show that: the algorithm can achieve better community detection results on real data sets and reduce the complexity of the algorithm while obtaining better results.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
