Network Representation Learning Methods Research Articles

Neighbor-Enhanced Representation Learning for Link Prediction in Dynamic Heterogeneous Attributed Networks

Dynamic link prediction aims to predict future connections among unconnected nodes in a network. It can be applied for friend recommendations, link completion, and other tasks. Network representation learning algorithms have demonstrated considerable effectiveness in various prediction tasks. However, most network representation learning algorithms are based on homogeneous networks and static networks for link prediction that do not consider rich semantic and dynamic information. Additionally, existing dynamic network representation learning methods neglect the neighborhood interaction structure of the node. In this work, we design a neighbor-enhanced dynamic heterogeneous attributed network embedding method (NeiDyHNE) for link prediction. In light of the impressive achievements of the heuristic methods, we learn the information of common neighbors and neighbors’ interaction in heterogeneous networks to preserve the neighbors proximity and common neighbors proximity. NeiDyHNE encodes the attributes and neighborhood structure of nodes as well as the evolutionary features of the dynamic network. More specifically, NeiDyHNE consists of the hierarchical structure attention module and the convolutional temporal attention module. The hierarchical structure attention module captures the rich features and semantic structure of nodes. The convolutional temporal attention module captures the evolutionary features of the network over time in dynamic heterogeneous networks. We evaluate our method and various baseline methods on the dynamic link prediction task. Experimental results demonstrate that our method is superior to baseline methods in terms of accuracy.

Research on the dynamic spread of information in social networks based on relationship strength theory and feedback mechanism

Introduction: Studying the main factors and related paths of rumor propagation contributes to the precise governance of rumor information in social networks. Most existing network representation learning methods do not fit with real-world information propagation networks well, and the network cannot effectively model the temporal characteristics and dynamic evolution features of rumor information propagation.Methods: Our study proposes a new dynamic network representation model for information propagation. Additionally, the study introduces a feedback mechanism where the latest node representations are fed back to neighboring nodes.Results: The method solves the problem of delayed network representation and improves network representation performance.Discussion: We conducted experimental simulations, and the results indicate that a higher level of trust contributes to stable group relationships and converging opinions, reducing the likelihood of opinion dispersion. Furthermore, novelty of topics, and interactivity between users, and opinion leaders exhibit distinct characteristics in guiding public opinion. The viewpoint evolution of the newly constructed dynamic network representation model aligns more closely with viewpoint evolution in real-world social networks.

WalkGAN: Network Representation Learning With Sequence-Based Generative Adversarial Networks.

Network representation learning, also known as network embedding, aims to learn the low-dimensional representations of vertices while capturing and preserving the network structure. For real-world networks, the edges that represent some important relationships between the vertices of a network may be missed and may result in degenerated performance. The existing methods usually treat missing edges as negative samples, thereby ignoring the true connections between two vertices in a network. To capture the true network structure effectively, we propose a novel network representation learning method called WalkGAN, where random walk scheme and generative adversarial networks (GAN) are incorporated into a network embedding framework. Specifically, WalkGAN leverages GAN to generate the synthetic sequences of the vertices that sufficiently simulate random walk on a network and further learn vertex representations from these vertex sequences. Thus, the unobserved links between the vertices are inferred with high probability instead of treating them as nonexistence. Experimental results on the benchmark network datasets demonstrate that WalkGAN achieves significant performance improvements for vertex classification, link prediction, and visualization tasks.

Contrastive representation learning on dynamic networks

Representation learning for dynamic networks is designed to learn the low-dimensional embeddings of nodes that can well preserve the snapshot structure, properties and temporal evolution of dynamic networks. However, current dynamic network representation learning methods tend to focus on estimating or generating observed snapshot structures, paying excessive attention to network details, and disregarding distinctions between snapshots with larger time intervals, resulting in less robustness for sparse or noisy networks. To alleviate these challenges, this paper proposes a contrastive mechanism for temporal representation learning on dynamic networks, inspired by the success of contrastive learning in visual and static network representation learning. This paper proposes a novel Dynamic Network Contrastive representation Learning (DNCL) model. Specifically, contrast objective functions are constructed using intra-snapshot and inter-snapshot contrasts to capture the network topology, node feature information, and network evolution information, respectively. Rather than estimating or generating ground-truth network features, the proposed approach maximizes mutual information between nodes from different time steps and views generated. The experimental results of link prediction, node classification, and clustering on several real-world and synthetic networks demonstrate the superiority of DNCL over state-of-the-art methods, indicating the effectiveness of the proposed approach for dynamic network representation learning.

Role-oriented representation learning via fusioning local and higher-order feature

Role-oriented representation learning extracts structural features by capturing the structural similarities of nodes to generate representations that preserve the structural equivalence, which is crucial for addressing the role discovery task of real networks. However, most studies directly combine different types of structural features and ignore the correlations among features, which is not enough to accurately portray node roles. Therefore, we propose a novel role-oriented network representation learning method RFLH that mines the correlations among features by normalizing flows to improve the performance on the role discovery tasks. We utilize the Variational Auto-Encoder (VAE) to generate the original representation distribution and learn the structural features of nodes by constraint of local and higher-order features, where local features are learned by the traditional variational module, while higher-order features are learned by the flow-based variational module that introduces normalizing flows to map the original representation distribution to a complex distribution. Moreover, we deduce the new loss by introducing the Jacobian determinant to Evidence Lower Bound (ELBO). Finally, we fuse local and higher-order features into the node representations, which are concatenated by the representations sampled from the original distribution and the new distribution, to generate the final node representations. Extensive experimental results on several real network datasets demonstrate that our model achieves superior performance compared to typical baseline methods.

Heterogeneous Network Representation Learning Approach for Ethereum Identity Identification

Recently, network representation learning has been widely used to mine and analyze network characteristics, and it is also applied to blockchain, but most of the embedding methods in blockchain ignore the heterogeneity of network, so it is difficult to accurately describe the characteristics of the transaction. As smart society evolves, Ethereum makes smart contracts reality, while the mine of transaction characteristics appearing on the Ethereum platform is scarce; thus, there is an urgent need to mine Ethereum from contract and transfer. In this article, we propose a heterogeneous network representation learning method to mine implicit information inside Ethereum transactions. Specifically, we construct an Ethereum transaction network by collecting transaction data from normal and phishing Ethereum accounts. Then, we propose a walk strategy that combines timestamps and transaction amounts to represent the information that occurs at the time of a transaction. To mine the types of nodes and edges, we use a heterogeneous network representation learning method to map the transaction network to a low-dimensional space. Finally, we improve the accuracy of the embedding results in the node classification task, which has important implications for Ethereum mining as well as identity recognition.

Dynamic network link prediction based on learning continuous time events

Dynamic network link prediction is a hot research problem in complex networks. Network representation learning can effectively learn the similarity of nodes and can be used for link prediction. Existing dynamic network representation learning methods mainly discrete window dynamic networks and then model them on static network snapshot graphs, which is difficult to effectively deal with dynamic networks with fine-grained temporal characteristics. In this paper, we propose a link prediction model that can learn complex temporal properties in dynamic networks. The model uses continuous time event sequences to represent dynamic networks, learns continuous temporal information and structural evolution features in the networks, and proposes a temporal attention-based information transfer mechanism to model the diffusion and aggregation of information in the networks. Finally, it transforms link prediction into a classification problem. The experiments are conducted on four real dynamic network datasets and simulated networks, using ap and auc as evaluation metrics. The experimental results of real networks demonstrate that the model can effectively learn the continuity of network evolution and obtain an effective node representation, thus improving the link prediction effect. The experimental results of the simulated network show that the effect of link prediction is related to the network model, but the model in this paper can still obtain better prediction results.

Network representation learning via improved random walk with restart

Real-world networks are usually sparse and high-dimensional representations that occupy considerable storage space and increase the computational complexity when performing network tasks. Recently, various methods of network representation learning that can effectively learn dense and low-dimensional network representations have been proposed. However, while these methods consider either the global or local structure of the network, the structures are not considered comprehensively. To address this problem, we propose a novel network representation learning method based on random walk with restart (NRL-RWR), which effectively captures the global and local structures of a network by means of an improved random walk with restart strategy. First, the random walk with restart is improved by an attention mechanism that assigns weights to edges by measuring the similarity between nodes. Second, the improved random walk with restart strategy has the ability to obtain the probability distribution of nodes, and always returns to the starting position with a certain probability in the process of walking, so that more global and local structures of the network can be retained. Finally, we construct an objective function based on Kullback–Leibler divergence, and we adopt negative sampling and edge sampling to optimize the objective function and reduce the computational complexity of network representation learning. Experimental results based on six real-world networks show that NRL-RWR outperforms state-of-the-art network representation learning methods in obtaining low-dimensional vector representations of networks.

Improving Link Prediction in Network Representation Learning with Feature Fusion and Local Outlier Factor

Complex networks are a diverse set of networks found in various fields, such as social, technological, and biological networks. One important task in complex network analysis is link prediction, which involves detecting missing links or predicting future link formation. Many methods based on network structure analysis have been developed for link prediction, including network representation learning (NRL) models that represent nodes in a low-dimensional space. Fusion-based attributed NRL methods are particularly effective, as they capture both content and structure information. However, NRL models for link prediction are binary classification models, which face challenges in identifying negative links and prioritizing predicted links. To address these challenges, we propose a novel approach that treats link prediction as a novelty detection problem. Our approach uses the Local Outlier Factor (LOF) algorithm to quantify the novelty of non-existent links based on the representations of existing links. Our experimental results show that our proposed approach outperforms existing methods, particularly when used with fusion-based attributed NRL models

Social Experience Guidance for College Students’ Entrepreneurship in the Social Network

The low success rate of entrepreneurship is quite common for contemporary college students, and its main reason can be attributed to their lack of social experience and entrepreneurial guidance, thus, it’s of certain practical significance to study the social experience guidance for college students’ entrepreneurship and this paper aims to explore this problem based on social network. At first, this paper introduced the formation mechanism of the social experience guidance for college students’ entrepreneurship, proposed a novel Social Network Representation Learning (SNRL) method for college students’ entrepreneurship, which could attain more information of social experience guidance from networks with isomorphic substructures. Then, in the social network of college students’ entrepreneurship, this paper discussed the extraction method of structural subgraph of neighborhood space of college students and other entrepreneurial subject nodes, and proposed a method for building sub-networks similar to the scale and development state in the social network of college students’ entrepreneurship, and realized the information sharing of social and entrepreneurial experiences among sub-networks. At last, this paper constructed a Social and Entrepreneurial Experience Guidance (SEEG) model, and verified its effectiveness in experiments.

Cross-domain entity identity association analysis and prediction based on representation learning

Cross-domain identity association of network entities is a significant research challenge and a vital issue of practical value in relationship discovery and service recommendation between things in the Internet of things, cyberspace resources surveying mapping, threat tracking, and intelligent recommendation. This task usually adds additional difficulty to the research in practical applications due to the need to link across multiple platforms. The existing entity identity association methods in cross-domain networks mainly use the attribute information, generated content, and network structure information of network user entities but do not fully use the inherent strong positioning characteristics of active nodes in the network. In this article, we analyzed the structural characteristics of existing relational networks. We found that the hub node has the role of identity association positioning, and the importance of identity association reflected by different nodes is different. Moreover, we creatively designed a network representation learning method. We proposed a supervised learning identity association model combined with a representation learning method. Experiments on the public data set show that using the identity association method proposed in this article, the ranking accuracy of user entity association similarity is about 30% and 25% higher than the existing two typical methods.

Anchor link prediction across social networks based on multiple consistency

With the development of social applications, users began to participate in multiple online social networks. If the same user in different social networks can be identified, it can provide powerful help for cross-platform recommendation, information diffusion, etc. Traditional methods use interlayer or intralayer structures alone for anchor link prediction and lack the comprehensive utilization of interlayer and intralayer structures. Therefore, this paper proposes an anchor link prediction method based on multiple consistency (MC). It uses interlayer structure information in an iterative manner and intralayer structure information through network representation learning. When using the intralayer structural information, a matrix factorization-based network representation learning method is used to learn embedding vectors that contain global structural features of nodes. A radial basis neural network is then trained as a mapping function to map embedding vectors in different spaces to the same space. Finally, the anchor links between node pairs are predicted by considering the interlayer and intralayer structures together. Experiments in several real networks show that our method generally outperforms the current approach.

Attribute Network Representation Learning with Dual Autoencoders

The purpose of attribute network representation learning is to learn the low-dimensional dense vector representation of nodes by combining structure and attribute information. The current network representation learning methods have insufficient interaction with structure when learning attribute information, and the structure and attribute information cannot be well integrated. In this paper, we propose an attribute network representation learning method for dual-channel autoencoder. One channel is for the network structure, and adopting the multi-hop attention mechanism is used to capture the node’s high-order neighborhood information and calculate the neighborhood weight; The other channel is for the node attribute information, and a low-pass Laplace filter is designed to iteratively obtain the attribute information in the neighborhood of the node. The dual-channel autoencoder ensures the learning of structure and attribute information respectively. The adaptive fusion module is constructed in this method to increase the acquisition of important information through the consistency and difference constraints of two kinds of information. The method trains encoders by supervising the joint reconstruction of loss functions of two autoencoders. Based on the node clustering task on four authentic open data sets, and compared with eight network representation learning algorithms in clustering accuracy, standardized mutual information and running time of some algorithms, the experimental results show that the proposed method is superior and reasonable.

Hypernetwork Representation Learning with Common Constraints of the Set and Translation

Different from conventional networks with only pairwise relationships among the nodes, there are also complex tuple relationships, namely the hyperedges among the nodes in the hypernetwork. However, most of the existing network representation learning methods cannot effectively capture the complex tuple relationships. Therefore, in order to resolve the above challenge, this paper proposes a hypernetwork representation learning method with common constraints of the set and translation, abbreviated as HRST, which incorporates both the hyperedge set associated with the nodes and the hyperedge regarded as the interaction relation among the nodes through the translation mechanism into the process of hypernetwork representation learning to obtain node representation vectors rich in the hypernetwork topology structure and hyperedge information. Experimental results on four hypernetwork datasets demonstrate that, for the node classification task, our method outperforms the other best baseline methods by about 1%. As for the link prediction task, our method is almost entirely superior to other baseline methods.

WebMILE

In recent years, we have seen the success of network representation learning (NRL) methods in diverse domains ranging from computational chemistry to drug discovery and from social network analysis to bioinformatics algorithms. However, each such NRL method is typically prototyped in a programming environment familiar to the developer. Moreover, such methods rarely scale out to large-scale networks or graphs. Such restrictions are problematic to domain scientists or end-users who want to scale a particular NRL method-of-interest on large graphs from their specific domain. In this work, we present a novel system, WebMILE to democratize this process. WebMILE can scale an unsupervised network embedding method written in the user's preferred programming language on large graphs. It provides an easy-to-use Graphical User Interface (GUI) for the end-user. The user provides the necessary input (embedding method file, graph, required packages information) through a simple GUI, and WebMILE executes the input network embedding method on the given input graph. WebMILE leverages a pioneering multi-level method, MILE (alternatively DistMILE if the user has access to a cluster), that can scale a network embedding method on large graphs. The language agnosticity is achieved through a simple Docker interface. In this demonstration, we will showcase how a domain scientist or end-user can utilize WebMILE to rapidly prototype and learn node embeddings of a large graph in a flexible and efficient manner - ensuring the twin goals of high productivity and high performance.

A supervised protein complex prediction method with network representation learning and gene ontology knowledge

BackgroundProtein complexes are essential for biologists to understand cell organization and function effectively. In recent years, predicting complexes from protein–protein interaction (PPI) networks through computational methods is one of the current research hotspots. Many methods for protein complex prediction have been proposed. However, how to use the information of known protein complexes is still a fundamental problem that needs to be solved urgently in predicting protein complexes.ResultsTo solve these problems, we propose a supervised learning method based on network representation learning and gene ontology knowledge, which can fully use the information of known protein complexes to predict new protein complexes. This method first constructs a weighted PPI network based on gene ontology knowledge and topology information, reducing the network's noise problem. On this basis, the topological information of known protein complexes is extracted as features, and the supervised learning model SVCC is obtained according to the feature training. At the same time, the SVCC model is used to predict candidate protein complexes from the protein interaction network. Then, we use the network representation learning method to obtain the vector representation of the protein complex and train the random forest model. Finally, we use the random forest model to classify the candidate protein complexes to obtain the final predicted protein complexes. We evaluate the performance of the proposed method on two publicly PPI data sets.ConclusionsExperimental results show that our method can effectively improve the performance of protein complex recognition compared with existing methods. In addition, we also analyze the biological significance of protein complexes predicted by our method and other methods. The results show that the protein complexes predicted by our method have high biological significance.

EEG Emotion Recognition Based on Self-attention Dynamic Graph Neural Networks.

In recent years, due to the fundamental role played by the central nervous system in emotion expression, electroencephalogram (EEG) signals have emerged as the most robust signals for use in emotion recognition and inference. Current emotion recognition methods mainly employ deep learning technology to learn the spatial or temporal representation of each channel, then obtain complementary information from different EEG channels by adopting a multi-modal fusion strategy. However, emotional expression is usually accompanied by the dynamic spatio-temporal evolution of functional connections in the brain. Therefore, the effective learning of more robust long-term dynamic representations for the brain's functional connection networks is a key to improving the EEG-based emotion recognition system. To address these issues, we propose a brain network representation learning method that employs self-attention dynamic graph neural networks to obtain the spatial structure information and temporal evolution characteristics of brain networks. Experimental results on the AMIGOS dataset show that the proposed method is superior to the state-of-the-art methods.

Network Representation Learning With Community Awareness and Its Applications in Brain Networks.

Previously network representation learning methods mainly focus on exploring the microscopic structure, i.e., the pairwise relationship or similarity between nodes. However, the mesoscopic structure, i.e., community structure, an essential property in real networks, has not been thoroughly studied in the network representation learning. We here propose a deep attributed network representation learning with community awareness (DANRL-CA) framework. Specifically, we design a neighborhood enhancement autoencoder module to capture the 2-step relations between node pairs. To explore the multi-step relations, we construct a community-aware skip-gram module based on the encoder. We introduce two variants of DANRL-CA, namely, DANRL-CA-AM and DANRL-CA-CSM, which incorporate the community information and attribute semantics into node neighbors with different methods. We compare two variant models with the state-of-the-art methods on four datasets for node classification and link prediction. Especially, we apply our models on a brain network. The superiority indicates the scalability and effectiveness of our method on various networks. Compared with DANRL-CA-AM, DANRL-CA-CSM can more flexibly coordinate the role of node attributes and community information in the process of network representation learning, and shows superiority in the networks with sparse topological structure and node attributes.

Discovering miRNAs Associated With Multiple Sclerosis Based on Network Representation Learning and Deep Learning Methods.

Identifying biomarkers of Multiple Sclerosis is important for the diagnosis and treatment of Multiple Sclerosis. The existing study has shown that miRNA is one of the most important biomarkers for diseases. However, few existing methods are designed for predicting Multiple Sclerosis-related miRNAs. To fill this gap, we proposed a novel computation framework for predicting Multiple Sclerosis-associated miRNAs. The proposed framework uses a network representation model to learn the feature representation of miRNA and uses a deep learning-based model to predict the miRNAs associated with Multiple Sclerosis. The evaluation result shows that the proposed model can predict the miRNAs associated with Multiple Sclerosis precisely. In addition, the proposed model can outperform several existing methods in a large margin.

Leveraging network representation learning and community detection for analyzing the activity profiles of adolescents

Human mobility analysis plays a crucial role in urban analysis, city planning, epidemic modeling, and even understanding neighborhood effects on individuals’ health. Often, these studies model human mobility in the form of co-location networks. We have recently seen the tremendous success of network representation learning models on several machine learning tasks on graphs. To the best of our knowledge, limited attention has been paid to identifying communities using network representation learning methods specifically for co-location networks. We attempt to address this problem and study user mobility behavior through the communities identified with latent node representations. Specifically, we select several diverse network representation learning models to identify communities from a real-world co-location network. We include both general-purpose representation models that make no assumptions on network modality as well as approaches designed specifically for human mobility analysis. We evaluate these different methods on data collected in the Adolescent Health and Development in Context study. Our experimental analysis reveals that a recently proposed method (LocationTrails) offers a competitive advantage over other methods with respect to its ability to represent and reflect community assignment that is consistent with extant findings regarding neighborhood racial and socio-economic differences in mobility patterns. We also compare the learned activity profiles of individuals by factoring in their residential neighborhoods. Our analysis reveals a significant contrast in the activity profiles of individuals residing in white-dominated versus black-dominated neighborhoods and advantaged versus disadvantaged neighborhoods in a major metropolitan city of United States. We provide a clear rationale for this contrastive pattern through insights from the sociological literature.