本文選題：屬性網(wǎng)絡(luò)圖 + 表示學(xué)習(xí)��； 參考：《華東師范大學(xué)》2017年碩士論文

【摘要】：隨著信息數(shù)據(jù)的爆發(fā)式增長(zhǎng),對(duì)于社交網(wǎng)絡(luò)、生物信息網(wǎng)絡(luò)等大規(guī)模網(wǎng)絡(luò)圖的分析與挖掘引起了越來(lái)越多的關(guān)注,網(wǎng)絡(luò)圖劃分、聚類、鏈接預(yù)測(cè)、社群搜索等問(wèn)題都已經(jīng)形成了較為獨(dú)立的研究方向。網(wǎng)絡(luò)表示學(xué)習(xí)(NetworkRepresentation Learning)任務(wù)的目標(biāo)是將圖中的節(jié)點(diǎn)用連續(xù)的低維向量表示,然后可以在向量空間下使用傳統(tǒng)的聚類、分類等方法完成進(jìn)一步的工作,因此被認(rèn)為是眾多圖挖掘工作的基礎(chǔ)。然而目前大多數(shù)的工作僅基于圖的拓?fù)浣Y(jié)構(gòu)訓(xùn)練向量,忽視了節(jié)點(diǎn)本身豐富的內(nèi)容信息。本文對(duì)前人的工作進(jìn)行改進(jìn),提出了基于隨機(jī)游走與詞向量模型的屬性網(wǎng)絡(luò)圖表示學(xué)習(xí)模型,本模型除了得到節(jié)點(diǎn)向量以外,還可以獲得屬性的低維向量表示,然后在所得向量的基礎(chǔ)上進(jìn)一步提出基于向量相似度的快速鏈接預(yù)測(cè)(Link Prediction)算法。本文主要包括以下四方面的工作:·屬性網(wǎng)絡(luò)圖表示學(xué)習(xí)模型本文面向?qū)傩跃W(wǎng)絡(luò)圖,提出了基于隨機(jī)游走與詞向量模型的表示學(xué)習(xí)模型,訓(xùn)練得到的節(jié)點(diǎn)與屬性向量能夠保留原始網(wǎng)絡(luò)圖的結(jié)構(gòu)完整性與屬性完整性�！傩跃W(wǎng)絡(luò)圖的鏈接預(yù)測(cè)算法在網(wǎng)絡(luò)表示學(xué)習(xí)模型的基礎(chǔ)上進(jìn)一步提出了鏈接預(yù)測(cè)算法。為了優(yōu)化效率,設(shè)計(jì)了 BMH(Balanced Min-Hash)方法代替?zhèn)鹘y(tǒng)的Min-Hash,將屬性與拓?fù)浣Y(jié)構(gòu)結(jié)合在一起生成最小簽名矩陣,然后引入局部敏感哈希技術(shù)(Local Sensitive Hash,簡(jiǎn)稱LSH)減少候選節(jié)點(diǎn)對(duì)的數(shù)量。·表示學(xué)習(xí)模型效果驗(yàn)證在多標(biāo)簽分類實(shí)驗(yàn)中,將本文提出的表示學(xué)習(xí)模型與幾種基于內(nèi)容或拓?fù)浣Y(jié)構(gòu)的模型進(jìn)行對(duì)比。實(shí)驗(yàn)表明本文模型用于分類的準(zhǔn)確率高,收斂速度快,且在不同的參數(shù)空間下魯棒性強(qiáng)�！ゆ溄宇A(yù)測(cè)算法準(zhǔn)確率驗(yàn)證實(shí)驗(yàn)驗(yàn)證了本文提出的基于表示學(xué)習(xí)的鏈接預(yù)測(cè)方法的準(zhǔn)確率,以及LSH與BMH的結(jié)合使用的加速效果。
[Abstract]:With the explosive growth of information data, more and more attention has been paid to the analysis and mining of large-scale network maps, such as social networks, biological information networks and so on. Community search and other issues have formed a relatively independent research direction. The goal of the network representation learning task is to represent the nodes in the graph as continuous low-dimensional vectors, and then use traditional clustering, classification and other methods in vector space to accomplish further work. Therefore, it is considered to be the basis of many map mining work. However, most of the work is only based on graph topology training vector, ignoring the rich content information of nodes themselves. In this paper, an attribute network representation learning model based on random walk and word vector model is proposed, which not only obtains node vectors, but also obtains low-dimensional vector representation of attributes. Then a fast link prediction algorithm based on vector similarity is proposed. This paper mainly includes the following four aspects: the representation learning model of attribute network graph. This paper presents a representation learning model based on random walk and word vector model, which is oriented to attribute network graph. The trained nodes and attribute vectors can preserve the structural integrity and attribute integrity of the original network graph. The link prediction algorithm of the attribute network graph is further proposed on the basis of the learning model of the network representation. In order to optimize the efficiency, the BMH(Balanced Min-Hash-based method is designed instead of the traditional Min-Hash. the attribute and topology are combined to generate the minimum signature matrix. Then the local sensitive hashing technique is introduced to reduce the number of candidate node pairs. It is shown that the effectiveness of the learning model is verified in the multi-label classification experiment. The representation learning model proposed in this paper is compared with several models based on content or topology. Experimental results show that the proposed model has high accuracy and fast convergence. And the link prediction algorithm is robust in different parameter spaces. The accuracy of the link prediction algorithm based on representation learning is verified by the experimental results, as well as the acceleration effect of the combination of LSH and BMH.
【學(xué)位授予單位】：華東師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：O157.5
，

本文編號(hào)：1907215