Representation Learning Method For Temporal Social Networks

With the development of mobile Internet,social network analysis has become a research hotspot recently.Temporal social networks(TSN)record the whole network’s growth process and evolution trend.The time-dimensional information maintained by TSN provides richer semantics for network analysis.Online social networks have brought opportunities and challenges for social network analysis.The representation problem is one of the biggest challenges.The traditional way of network representation based on a graph is not suitable for today’s social networks,and it suffers from many problems,such as low storage efficiency,high computational complexity,inability to apply mature machine learning algorithms,etc.Network representation learning(NRL),also known as network embedding,is one of the critical methods for social network analysis.NRL is committed to learning the low dimensional and dense vector representation of network nodes to preserve the topology and internal properties of the network.At present,most NRL methods are devoted to static social networks,while the research on temporal social network representation learning is still in its infancy.While providing more time-dimensional information,TSN also poses a series of challenges.Existing research suffer from the following problems:1)most of them can hardly capture the node similarity accurately and preserve the highly nonlinear network structure;2)most of them can not preserve the temporal network topology and node attribute simultaneously;3)most of them lack the ability to learn the representation of network evolution mechanisms;4)most of them has no noise robustness and can not reduce the impact of network noise on the accuracy of representation learning.1.This dissertation proposes a high-order nonlinear information preservation representation learning method for the first problem.Firstly,we define three kinds of temporal proximities of nodes in TSN based on a time exponential decay model.Then,we propose a temporal random walk algorithm to embed the temporal proximity into the walking path.Finally,we propose a novel deep guided auto-encoder to learn node representations for networks.This auto-encoder has multiple layers of nonlinear functions to capture the highly nonlinear network structure.By training the proposed auto-encoder with the walking path set,our method can preserve the temporal proximity and highly nonlinear structure of TSN.Experimental results on six temporal social networks demonstrate the effectiveness of the proposed method.2.This dissertation proposes an attributed temporal network embedding method for the second problem.The core of this method is to dynamically,and orderly aggregate node attributes to generate node representation vectors based on the topology of TSN.We propose a biased neighbor sampling algorithm for neighbor nodes sampling by exploring the historical interaction information between nodes.This algorithm is based on the point process to model the relationship strength between node vi and its neighborhood.After sampling neighbor nodes,this method proposes an inductive representation learning algorithm,which trains an inductive graph convolution neural network model for network representation learning.Experimental results on four attributed temporal social networks demonstrate the effectiveness of the proposed method.3.This dissertation proposes a triad-based network evolution mechanism representation learning method for the third problem.This method takes a triad transition matrix(TTM)as a carrier to represent the abstract evolution mechanism.Firstly,we analyze the feasibility of using the TTM as the carrier by counting the number distribution of different triads in a mechanism controllable artificial network.Then,we propose a CNN-LSTM model to learn the evolution law of TTM.Finally,we propose a link prediction algorithm based on TTM to verify the ability of this method.The results in real social networks and evolution mechanism controllable artificial networks indicate that the proposed method can well preserve the abstract evolution mechanism of TSN.Experimental results on model networks and real-world networks demonstrate the effectiveness of the proposed method.4.This dissertation proposes a noise-resilient high-order similarity preserving temporal network representation learning method for the fourth problem.Firstly,considering the time-dimensional information of TSN,we modify five node similarity indexes and define a comprehensive similarity index.Based on the comprehensive index,we propose a high-order similarity construction algorithm to construct a high-order temporal similarity matrix S.An accurate high-order similarity can serve as a metric of the authenticity of the observed network structure.Then,we correct the first-order temporal similarity based on the constructed S and propose a correction matrix construction algorithm to construct a correction matrix C.Finally,we propose an embedded model for network representation learning.The model considers both C and S.By optimizing the model,this method can effectively save the real network structure of TSN.Experimental results on four noisy temporal social networks demonstrate the effectiveness of the proposed method.