Network Representation Learning Algorithms Research Articles

Learning Universal Network Representation via Link Prediction by Graph Convolutional Neural Network

Network representation learning algorithms, which aim at automatically encoding graphs into low-dimensional vector representations with a variety of node similarity definitions, have a wide range of downstream applications. Most existing methods either have low accuracies in downstream tasks or a very limited application field, such as article classification in citation networks. In this paper, we propose a novel network representation method, named Link Prediction based Network Representation (LPNR), which generalizes the latest graph neural network and optimizes a carefully designed objective function that preserves linkage structures. LPNR can not only learn meaningful node representations that achieve competitive accuracy in node centrality measurement and community detection but also achieve high accuracy in the link prediction task. Experiments prove the effectiveness of LPNR on three real-world networks. With the mini-batch and fixed sampling strategy, LPNR can learn the embedding of large graphs in a few hours.

Network Representation Learning Algorithm Combined with Node Text Information

In a network data analysis task, network representation learning play an important role. It can obtain a low-dimensional representative vector from high dimensional features of nodes which will promote the efficiency of downstream analysis task. Many algorithms mainly based on the structure information of the network but for a complex network, there is a lot kinds of feature information available for representation learning which has an important impact on network data analysis task. Therefore, we propose a network representation learning algorithm that combines node text information. Before our algorithm, we encode the information of the nodes including structure and text, and the strategy of fusion is adopted in advance which splice structure and text information. And then we feed the splicing results into the neural network which is a multi-layer feedforward neural network with a tower structure to learn the nonlinear structure information of complex networks. Finally, we design the structure loss function that preserve structure similarity and text loss function that preserve text information respectively. And we use the joint training to make two aspects information interact continuously. We conduct experiment to evaluate our algorithm. The results on two real word networks show our algorithm has better performance compared with traditional algorithms.

Semisupervised Community Preserving Network Embedding with Pairwise Constraints

Network embedding aims to learn the low-dimensional representations of nodes in networks. It preserves the structure and internal attributes of the networks while representing nodes as low-dimensional dense real-valued vectors. These vectors are used as inputs of machine learning algorithms for network analysis tasks such as node clustering, classification, link prediction, and network visualization. The network embedding algorithms, which considered the community structure, impose a higher level of constraint on the similarity of nodes, and they make the learned node embedding results more discriminative. However, the existing network representation learning algorithms are mostly unsupervised models; the pairwise constraint information, which represents community membership, is not effectively utilized to obtain node embedding results that are more consistent with prior knowledge. This paper proposes a semisupervised modularized nonnegative matrix factorization model, SMNMF, while preserving the community structure for network embedding; the pairwise constraints (must-link and cannot-link) information are effectively fused with the adjacency matrix and node similarity matrix of the network so that the node representations learned by the model are more interpretable. Experimental results on eight real network datasets show that, comparing with the representative network embedding methods, the node representations learned after incorporating the pairwise constraints can obtain higher accuracy in node clustering task and the results of link prediction, and network visualization tasks indicate that the semisupervised model SMNMF is more discriminative than unsupervised ones.

HSNR: A Network Representation Learning Algorithm Using Hierarchical Structure Embedding

Vertices in the same group tend to connect densely, and usually share common attributes. Groups of different sizes reflect the relations of vertices in different ranges, and also reflect the features of different orders of the network. In this work, we propose a novel network representation learning algorithm by introducing group features of vertices of different orders to learn more discriminative network representations, named as network representation learning algorithm using Hierarchical structure embedding (HSNR). HSNR algorithm firstly constructs hierarchical relations of network structures of different orders based on greedy algorithm and modularity. In order to introduce hierarchical features into the network representation learning model, HSNR algorithm then introduces the idea of multi-relational modeling from knowledge representation, and converts the hierarchical relations into the triplet form between vertices. Finally, HSNR proposes a joint learning model embedding vertex triplets into the network representations. The experimental results show that the HSRN algorithm presented has an excellent performance in network vertex classification task on three real-world datasets.

Network representation learning: a systematic literature review

Omnipresent network/graph data generally have the characteristics of nonlinearity, sparseness, dynamicity and heterogeneity, which bring numerous challenges to network related analysis problem. Recently, influenced by the excellent ability of deep learning to learn representation from data, representation learning for network data has gradually become a new research hotspot. Network representation learning aims to learn a project from given network data in the original topological space to low-dimensional vector space, while encoding a variety of structural and semantic information. The vector representation obtained could effectively support extensive tasks such as node classification, node clustering, link prediction and graph classification. In this survey, we comprehensively present an overview of a large number of network representation learning algorithms from two clear points of view of homogeneous network and heterogeneous network. The corresponding algorithms are deeply analyzed. Extensive applications are introduced in an all-round way, and related experiments are conducted to validate the typical algorithms. Finally, we point out five future promising directions for next research in terms of theory and application.

The Network Representation Learning Algorithm Based on Semi-Supervised Random Walk

As an important tool of social network analysis, network representation learning also called network embedding maps the network to a latent space and learns low-dimensional and dense real vectors of nodes, while preserving the structure and internal attributes of network. The learned representations or embedding vectors can be used for node clustering, link prediction, network visualization and other tasks for network analysis. Most of the existing network representation learning algorithms mainly focus on the preservation of micro or macro network structure, ignoring the mesoscopic community structure information. Although a few network embedding methods are proposed to preserve the community structure, they all ignore the prior information about communities. Inspired by the semi-supervised community detection in complex networks, in this article, a novel Semi-Supervised DeepWalk method(SSDW) is proposed for network representation learning, which successfully preserves the community structure of network in the embedding space. Specifically, a semi-supervised random walk sampling method which effectively integrates the pairwise constraints is proposed. By doing so, the SSDW model can guide the transition probability in the random walk process and obtain the node context sequence in line with the prior knowledge. The experimental results on eight real networks show that comparing with the popular network embedding methods, the node representation vectors integrating pairwise constraints into the random walk process can obtain higher accuracy on node clustering task, and the results of link prediction, network visualization tasks indicate that the semi-supervised model SSDW is more discriminative than unsupervised ones.

Network Representation Learning Guided by Partial Community Structure

Network Representation Learning (NRL) is an effective way to analyse large scale networks (graphs). In general, it maps network nodes, edges, subgraphs, etc. onto independent vectors in a low dimension space, thus facilitating network analysis tasks. As community structure is one of the most prominent mesoscopic structure properties of real networks, it is necessary to preserve community structure of networks during NRL. In this paper, the concept of k-step partial community structure is defined and two Partial Community structure Guided Network Embedding (PCGNE) methods, based on two popular NRL algorithms (DeepWalk and node2vec respectively), for node representation learning are proposed. The idea behind this is that it is easier and more cost-effective to find a higher quality 1-step partial community structure than a higher quality whole community structure for networks; the extracted partial community information is then used to guide random walks in DeepWalk or node2vec. As a result, the learned node representations could preserve community structure property of networks more effectively. The two proposed algorithms and six state-of-the-art NRL algorithms were examined through multi-label classification and (inner community) link prediction on eight synthesized networks: one where community structure property could be controlled, and one real world network. The results suggested that the two PCGNE methods could improve the performance of their own based algorithm significantly and were competitive for node representation learning. Especially, comparing against used baseline algorithms, PCGNE methods could capture overlapping community structure much better, and thus could achieve better performance for multi-label classification on networks that have more overlapping nodes and/or larger overlapping memberships.

Semi-GSGCN: Social Robot Detection Research with Graph Neural Network

Malicious social robots are the disseminators of malicious information on social networks, which seriously affect information security and network environments. Efficient and reliable classification of social robots is crucial for detecting information manipulation in social networks. Supervised classification based on manual feature extraction has been widely used in social robot detection. However, these methods not only involve the privacy of users but also ignore hidden feature information, especially the graph feature, and the label utilization rate of semi-supervised algorithms is low. Aiming at the problems of shallow feature extraction and low label utilization rate in existing social network robot detection methods, in this paper a robot detection scheme based on weighted network topology is proposed, which introduces an improved network representation learning algorithm to extract the local structure features of the network, and combined with the graph convolution network (GCN) algorithm based on the graph filter, to obtain the global structure features of the network. An end-to-end semi-supervised combination model (Semi-GSGCN) is established to detect malicious social robots. Experiments on a social network dataset (cresci-rtbust-2019) show that the proposed method has high versatility and effectiveness in detecting social robots. In addition, this method has a stronger insight into robots in social networks than other methods.

Network representation based on the joint learning of three feature views

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.

Construction and Analysis of Molecular Association Network by Combining Behavior Representation and Node Attributes

A key aim of post-genomic biomedical research is to systematically understand and model complex biomolecular activities based on a systematic perspective. Biomolecular interactions are widespread and interrelated, multiple biomolecules coordinate to sustain life activities, any disturbance of these complex connections can lead to abnormal of life activities or complex diseases. However, many existing researches usually only focus on individual intermolecular interactions. In this work, we revealed, constructed, and analyzed a large-scale molecular association network of multiple biomolecules in human by integrating associations among lncRNAs, miRNAs, proteins, drugs, and diseases, in which various associations are interconnected and any type of associations can be predicted. We propose Molecular Association Network (MAN)–High-Order Proximity preserved Embedding (HOPE), a novel network representation learning based method to fully exploit latent feature of biomolecules to accurately predict associations between molecules. More specifically, network representation learning algorithm HOPE was applied to learn behavior feature of nodes in the association network. Attribute features of nodes were also adopted. Then, a machine learning model CatBoost was trained to predict potential association between any nodes. The performance of our method was evaluated under five-fold cross validation. A case study to predict miRNA-disease associations was also conducted to verify the prediction capability. MAN-HOPE achieves high accuracy of 93.3% and area under the receiver operating characteristic curve of 0.9793. The experimental results demonstrate the novelty of our systematic understanding of the intermolecular associations, and enable systematic exploration of the landscape of molecular interactions that shape specialized cellular functions.

Tri-party deep network representation learning using inductive matrix completion

Most existing network representation learning algorithms focus on network structures for learning. However, network structure is only one kind of view and feature for various networks, and it cannot fully reflect all characteristics of networks. In fact, network vertices usually contain rich text information, which can be well utilized to learn text-enhanced network representations. Meanwhile, Matrix-Forest Index (MFI) has shown its high effectiveness and stability in link prediction tasks compared with other algorithms of link prediction. Both MFI and Inductive Matrix Completion (IMC) are not well applied with algorithmic frameworks of typical representation learning methods. Therefore, we proposed a novel semi-supervised algorithm, tri-party deep network representation learning using inductive matrix completion (TDNR). Based on inductive matrix completion algorithm, TDNR incorporates text features, the link certainty degrees of existing edges and the future link probabilities of non-existing edges into network representations. The experimental results demonstrated that TFNR outperforms other baselines on three real-world datasets. The visualizations of TDNR show that proposed algorithm is more discriminative than other unsupervised approaches.

An Optimized Network Representation Learning Algorithm Using Multi-Relational Data

Representation learning aims to encode the relationships of research objects into low-dimensional, compressible, and distributed representation vectors. The purpose of network representation learning is to learn the structural relationships between network vertices. Knowledge representation learning is oriented to model the entities and relationships in knowledge bases. In this paper, we first introduce the idea of knowledge representation learning into network representation learning, namely, we propose a new approach to model the vertex triplet relationships based on DeepWalk without TransE. Consequently, we propose an optimized network representation learning algorithm using multi-relational data, MRNR, which introduces the multi-relational data between vertices into the procedures of network representation learning. Importantly, we adopted a kind of higher order transformation strategy to optimize the learnt network representation vectors. The purpose of MRNR is that multi-relational data (triplets) can effectively guide and constrain the procedures of network representation learning. The experimental results demonstrate that the proposed MRNR can learn the discriminative network representations, which show better performance on network classification, visualization, and case study tasks compared to the proposed baseline algorithms in this paper.

Multi-View Network Representation Learning Algorithm Research

Network representation learning is a key research field in network data mining. In this paper, we propose a novel multi-view network representation algorithm (MVNR), which embeds multi-scale relations of network vertices into the low dimensional representation space. In contrast to existing approaches, MVNR explicitly encodes higher order information using k-step networks. In addition, we introduce the matrix forest index as a kind of network feature, which can be applied to balance the representation weights of different network views. We also research the relevance amongst MVNR and several excellent research achievements, including DeepWalk, node2vec and GraRep and so forth. We conduct our experiment on several real-world citation datasets and demonstrate that MVNR outperforms some new approaches using neural matrix factorization. Specifically, we demonstrate the efficiency of MVNR on network classification, visualization and link prediction tasks.

Utilizing computational trust to identify rumor spreaders on Twitter

Ubiquitous use of social media such as microblogging platforms opens unprecedented chances for false information to diffuse online. Facing the challenges in such a so-called “post-fact” era, it is very important for intelligent systems to not only check the veracity of information but also verify the authenticity of the users who spread the information, especially in time-critical situations such as real-world emergencies, where urgent measures have to be taken for stopping the spread of fake information. In this work, we propose a novel machine-learning-based approach for automatic identification of the users who spread rumorous information on Twitter by leveraging computational trust measures, in particular the concept of Believability. We define believability as a measure for assessing the extent to which the propagated information is likely being perceived as truthful or not based on the proxies of trust such as user’s retweet and reply behaviors in the network. We hypothesize that the believability between two users is proportional to the trustingness of the retweeter/replier and the trustworthiness of the tweeter, which are complementary to one another for representing user trust and can be inferred from trust proxies using a variant of HITS algorithm. With the trust network edge-weighted by believability scores, we apply network representation learning algorithms to generate user embeddings, which are then used to classify users into rumor spreaders or not based on recurrent neural networks (RNN). Experimented on a large real-world rumor dataset collected from Twitter, it is demonstrated that our proposed RNN-based method can effectively identify rumor spreaders and outperform four more straightforward, non-RNN models with large margin.

Network representation learning: an overview

Networks are important ways of representing objects and their relationships. A key problem in the study of networks is how to represent the network information properly. With the developments in machine learning, feature learning of network vertices has become an important area of study. Network representation learning algorithms turn network information into dense, low-dimensional real-valued vectors that can be used as inputs for existing machine learning algorithms. For example, the representation of vertices can be fed to a classifier such as a Support Vector Machine (SVM) for vertex classification. In addition, the representations can be used for visualization by taking the representations as points in a Euclidean space. The study of network representation learning has attracted the attention of many researchers. In this article, recent works on network representation learning are introduced and summarized.