發(fā)布時(shí)間：2018-10-15 18:24

【摘要】：社區(qū)結(jié)構(gòu)是復(fù)雜網(wǎng)絡(luò)的重要特征之一,社區(qū)發(fā)現(xiàn)對(duì)研究網(wǎng)絡(luò)結(jié)構(gòu)有重要的應(yīng)用價(jià)值.k-均值等經(jīng)典聚類算法是解決社區(qū)發(fā)現(xiàn)問(wèn)題的一類基本方法.然而,在處理網(wǎng)絡(luò)的高維矩陣時(shí),使用這些經(jīng)典聚類方法得到的社區(qū)往往不夠準(zhǔn)確.提出一種基于深度稀疏自動(dòng)編碼器的社區(qū)發(fā)現(xiàn)算法CoDDA(a community detection algorithm based on deep sparse autoencoder),嘗試提高使用這些經(jīng)典方法處理高維鄰接矩陣進(jìn)行社區(qū)發(fā)現(xiàn)的準(zhǔn)確性.首先,提出基于跳數(shù)的處理方法,對(duì)稀疏的鄰接矩陣進(jìn)行優(yōu)化處理,得到的相似度矩陣不僅能夠反映網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)中相連節(jié)點(diǎn)間的相似關(guān)系,同時(shí)還反映了不相連節(jié)點(diǎn)間的相似關(guān)系.然后,基于無(wú)監(jiān)督深度學(xué)習(xí)方法構(gòu)建深度稀疏自動(dòng)編碼器,對(duì)相似度矩陣進(jìn)行特征提取,得到低維的特征矩陣.與鄰接矩陣相比,特征矩陣對(duì)網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)有更強(qiáng)的特征表達(dá)能力.最后,使用k-均值算法對(duì)低維特征矩陣聚類得到社區(qū)結(jié)構(gòu).實(shí)驗(yàn)結(jié)果顯示:與6種典型的社區(qū)發(fā)現(xiàn)算法相比,CoDDA算法能夠發(fā)現(xiàn)更準(zhǔn)確的社區(qū)結(jié)構(gòu).同時(shí),參數(shù)實(shí)驗(yàn)結(jié)果顯示,CoDDA算法發(fā)現(xiàn)的社區(qū)結(jié)構(gòu)比直接使用高維鄰接矩陣的基本k-均值算法發(fā)現(xiàn)的社區(qū)結(jié)構(gòu)更為準(zhǔn)確.
[Abstract]:Community structure is one of the important characteristics of complex networks. Community discovery has important application value in studying network structure. The classical clustering algorithm such as k- mean is a kind of basic method to solve community discovery problem. However, when dealing with the high dimensional matrix of the network, the communities obtained by these classical clustering methods are often inaccurate. A community discovery algorithm based on deep sparse automatic encoder (CoDDA (a community detection algorithm based on deep sparse autoencoder),) is proposed to improve the accuracy of community discovery by using these classical methods to deal with high-dimensional adjacency matrix. First of all, a method based on hops is proposed to optimize the sparse adjacent matrix. The similarity matrix can not only reflect the similarity relationship between connected nodes in the network topology. At the same time, it also reflects the similarity between disconnected nodes. Then, based on the unsupervised depth learning method, the depth sparse automatic encoder is constructed, and the feature extraction of similarity matrix is carried out, and the low-dimensional feature matrix is obtained. Compared with the adjacent matrix, the feature matrix has a stronger ability to express the network topology. At last, we use k- mean algorithm to cluster the low dimensional feature matrix to get the community structure. Experimental results show that CoDDA algorithm can find more accurate community structure than six typical community discovery algorithms. At the same time, the experimental results show that the community structure discovered by the CoDDA algorithm is more accurate than that by the basic kmean algorithm using the high-dimensional adjacency matrix directly.
【作者單位】： 清華大學(xué)軟件學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(61373023)~~
【分類號(hào)】：O157.5

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 周小平;梁循;張海燕;;基于R-C模型的微博用戶社區(qū)發(fā)現(xiàn)[J];軟件學(xué)報(bào);2014年12期

2 黃發(fā)良;張師超;朱曉峰;;基于多目標(biāo)優(yōu)化的網(wǎng)絡(luò)社區(qū)發(fā)現(xiàn)方法[J];軟件學(xué)報(bào);2013年09期

3 淦文燕;赫南;李德毅;王建民;;一種基于拓?fù)鋭?shì)的網(wǎng)絡(luò)社區(qū)發(fā)現(xiàn)方法[J];軟件學(xué)報(bào);2009年08期

4 楊楠,弓丹志,李_，

本文編號(hào)：2273437