Network representation based on the joint learning of three feature views

Abstract

Network representation learning plays an important role in the field of network data mining. By embedding network structures and other features into the representation vector space of low dimensions, network representation learning algorithms can provide high-quality feature input for subsequent tasks, such as network link prediction, network vertex classification, and network visualization. The existing network representation learning algorithms can be trained based on the structural features, vertex texts, vertex tags, community information, etc. However, there exists a lack of algorithm of using the future evolution results of the networks to guide the network representation learning. Therefore, this paper aims at modeling the future network evolution results of the networks based on the link prediction algorithm, introducing the future link probabilities between vertices without edges into the network representation learning tasks. In order to make the network representation vectors contain more feature factors, the text features of the vertices are also embedded into the network representation vectors. Based on the above two optimization approaches, we propose a novel network representation learning algorithm, Network Representation learning algorithm based on the joint optimization of Three Features (TFNR). Based on Inductive Matrix Completion (IMC), TFNR algorithm introduces the future probabilities between vertices without edges and text features into the procedure of modeling network structures, which can avoid the problem of the network structure sparse. Experimental results show that the proposed TFNR algorithm performs well in network vertex classification and visualization tasks on three real citation network datasets.

Network Embedding the Protein–Protein Interaction Network for Human Essential Genes Identification

“…Network embedding is an efficient method to mine the useful information from the network, which converts the network nodes into a vector of low dimensional space while maximally preserves the network structural information and the network properties. There are many network embedding methods [33][34][35][36][37]. In this work, we learn the vector representation of the nodes in the human PPI network by using a random walk-based network embedding method.…”

Collaborative city digital twin for the COVID-19 pandemic: A federated learning solution

“…Deep learning-based epidemic control: Historical insights from temporal infection data have been crucial for epidemic control and prevention, and could benefit other problems in smart city systems [13,14] or enhanced social network analysis [15] . Deep learningbased techniques have demonstrated a remarkable performance to model such temporal correlations and recognize multiple patterns [16,17] , including the deep neural network-based short-term and high-resolution epidemic forecasting for influenza-like illness [18] , the semi-supervised deep learning framework that integrates computational epidemiology and social media mining techniques for epidemic simulation, called SimNest [19] and EpiRP [20] , which use representational learning methods to capture the dynamic characteristics of epidemic spreading on social networks for epidemicsoriented clustering and classification.…”

Security-driven distributed platforms for intellectual property resource provision - a case study of TSITE IP

“…Small to daily necessities, as well as work needs, large to the garage are frequent online transactions and transactions. Products with physical objects as carriers are easy to trade on the Internet because of their "tangible" characteristics [10,11]. However, it cannot prove that intangible services without physical objects cannot be sold online.…”