Structural Analysis and Link Prediction in Dynamic Networks of Web Services

Link prediction aims to find the missing link in current networks or estimate the likelihood the link will appear in the future. In many real-world scenarios, networks can be massive and drastically evolving. Many recent works concentrated on how to solve the procession of massive data, which cares less about the effects of the temporal information. In some dynamic networks, the edge that appears a long time ago will have fewer effects on the appearance of edges in the future. The accuracy of link prediction in dynamic networks can be further improved by adding temporal information in prediction measures. In this paper, we mainly explore the effects of the link temporal information in the graph stream link prediction. We design a graph stream-based framework to solve link prediction problems in dynamic networks which can provide a convenient platform to implement different link prediction methods for dynamic networks, and evaluate these methods on a fair basis. Then, we proposed the Time Decay-based Link Prediction (TDLP) method to improve the efficient of link prediction problem in the dynamic networks. TDLP extends the neighborhood-based measure with time decay functions in graph stream scenarios which can handle temporal information and massive data. Experiment results demonstrate that the accuracy of link prediction for dynamic networks can be efficiently improved in our TDLP method.

Dynamic networks are inherently evolutionary in nature where the characteristics, behaviour and activities of their constituents (i.e., actors and links) change temporally. In regards to time-evolving model in social network analyses, link prediction supports the understanding of the rationale behind the underlying growth mechanisms of social networks. Mining the temporal patterns of actor-level evolutionary changes in regards to their network neighbourhood, and community-based dynamic information may suitably be used for the purpose of dynamic link prediction. Considering the evolutionary aspects of mesoscale network structure (i.e., community), this study sought to build dynamic similarity metrics or dynamic features to measure similarity/proximity between actor-pairs. A supervised link prediction model was set out where these features were employed as instance features and performances were compared against an existing topological similarity-based link prediction metric. High-performance scores achieved by these dynamic feature, examined in this study, represent them as prospective candidates not only for dynamic link prediction task but also understanding of underlying network evolution mechanism.

Network embedding based link prediction in dynamic networks

Link prediction in dynamic networks is an important task with many real-life applications in different domains, such as social networks, cyber-physical systems, and bioinformatics. There are two key processes in dynamic networks: network structural evolution and network temporal evolution, where the former represents interdependency between entities and their neighbors in the network at each timestamp, while the latter captures the evolving behavior of the entire network from the current timestamp to the next. Structural evolution generally assumes that a node is more likely to co-evolve with its neighbors in the near future. Temporal evolution focuses on the trend of network evolution as a whole, based on the accumulation of historical data. It is thus essential to use characteristics of both structural and temporal evolutions to emulate complex behaviors of dynamic networks. However, very few existing work considered both processes. In addition, real-life networks are often very sparse with limited observed links. A missing link between two nodes does not always imply that the two nodes do not have a relation in reality, especially when they share many common neighbors. Most existing methods only focus on the first-order proximity of networks, which is usually insufficient to capture the relationships among nodes.

We consider the problem of link prediction in dynamic networks under the condition of a set of snapshots of the networks. To address the nonlinear transitional patterns in network structures, we propose an approach that incorporates the historical linkage and neighboring information into the restricted Boltzmann machine (RBM) model by adding temporal and neighboring connections between the hidden and visible layers. Based on this, we give an algorithm to train the model parameters. Experiments on synthetic dynamic networks verify the effectiveness of our method.

The prediction of mobility, topology and traffic is an effective technique to improve the performance of various network systems, which can be generally represented as the temporal link prediction problem. In this paper, we propose a novel adaptive multiple non-negative matrix factorization (AM-NMF) method from the view of network embedding to cope with such problem. Under the framework of non-negative matrix factorization (NMF), the proposed method embeds the dynamic network into a low-dimensional hidden space, where the characteristics of different network snapshots are comprehensively preserved. Especially, our new method can effectively incorporate the hidden information of different time slices, because we introduce a novel adaptive parameter to automatically adjust the relative contribution of different terms in the uniform model. Accordingly, the prediction result of future network topology can be generated by conducting the inverse process of NMF form the shared hidden space. Moreover, we also derive the corresponding solving strategy whose convergence can be ensured. As an illustration, the new model will be applied to various network datasets such as human mobility networks, vehicle mobility networks, wireless mesh networks and data center networks. Experimental results show that our method outperforms some other state-of-the-art methods for the temporal link prediction of both unweighted and weighted networks.

Link prediction in multilayer networks using weighted reliable local random walk algorithm

On-line social networks (OSNs) often contain many different types of relationships between users. When studying the structure of OSNs such as Facebook, two of the most commonly studied networks are friendship and interaction networks. The link prediction problem in friendship networks has been heavily studied. There has also been prior work on link prediction in interaction networks,independent of friendship networks. In this paper, we study the predictive power of combining friendship and interaction networks. We hypothesize that, by leveraging friendship networks, we can improve the accuracy of link prediction in interaction networks. We augment several interaction link prediction algorithms to incorporate friendships and predicted friendships. From experiments on Facebook data, we find that incorporating friendships into interaction link prediction algorithms results in higher accuracy, but incorporating predicted friendships does not when compared to incorporating current friendships.

Introduction Network representation can give a holistic view of relationships for biomedical entities through network topology. Link prediction estimates the probability of link formation between the pair of unconnected nodes. In the drug discovery process, the link prediction method not only enables the detection of connectivity patterns but also predicts the effects of one biomedical entity to multiple entities simultaneously and vice versa, which is useful for many applications. Areas covered The authors provide a comprehensive overview of network link prediction in drug discovery. Link prediction methodologies such as similarity-based approaches, embedding-based approaches, probabilistic model-based approaches, and preprocessing methods are summarized with examples. In addition to describing their properties and limitations, the authors discuss the applications of link prediction in drug discovery based on the relationship between biomedical concepts. Expert opinion Link prediction is a powerful method to infer the existence of novel relationships in drug discovery. However, link prediction has been hampered by the sparsity of data and the lack of negative links in biomedical networks. With preprocessing to balance positive and negative samples and the collection of more data, the authors believe it is possible to develop more reliable link prediction methods that can become invaluable tools for successful drug discovery.

Link prediction methods can help to reconstruct systems from incomplete datasets, to understand the structure dynamic complex networks, and to predict future interactions in evolving networks. Link prediction in multiplex networks is the problem of finding missing links between users based on information from other layers. Although the link prediction problem has been widely studied in multiplex networks, most methods do not consider both interlayer and intralayer features at the same time. Similarity metrics are one of the most common approaches to solving the link prediction problem. However, the development of similarity metrics over multiple layers with the definition of multiplex networks has become an important challenge that has caught the attention of many researchers. In this article, a novel similarity metric is introduced by considering reliable paths between users for link prediction in multiplex networks. The proposed method maps the network to a weighted network by extracting different interlayer and intralayer features from multiplex networks. Finally, the proposed similarity metric develops the FriendLink metric by considering the weight of links and reliable paths. The proposed method is evaluated in comparison with classical similarity metrics and equivalence algorithms such as SEM-Path, LPIS, and SOIDP. Two real datasets based on multiplex networks including Twitter–Foursquare and Twitter–Instagram have been used to evaluate. Experiments prove the superiority of link prediction in the proposed method over other algorithms.

Link prediction is one of the most important and challenging tasks in complex network analysis, which aims to predict the existence of unknown links based on the known information in the network. As critical topological properties in the network, node’s degree and clustering coefficient are well-suited for describing the tightness of connection between nodes. The importance of node can affect the possibility of link existence to a certain extent. By analyzing the impact of different centrality on links, which concluded that the degree centrality and proximity centrality have the greatest influence on network link prediction. A link prediction algorithm combines importance of node and network topological properties, called DCCLP, is proposed in this paper, the symmetry of the adjacency matrix is considered in the DCCLP link prediction algorithm to further describe the structural similarity of network nodes. In the training phase of the DCCLP algorithm, the maximized AUC indicator in the training set as the objective, and the optimal parameters are estimated by utilizing the White Shark Optimization algorithm. Then the prediction accuracy of the DCCLP algorithm is evaluated in the test set. By experimenting on twenty-one networks with different scales, and comparing with existing algorithms, the experimental results show that the effectiveness and feasibility of DCCLP algorithm, and further illustrate the importance of the degree centrality of node pairs and proximity centrality of nodes to improve the prediction accuracy of link prediction.

Link prediction in complex networks aims to mine hidden or to-be-generated links between network nodes, which plays a significant role in fields such as the cold start of recommendation systems, knowledge graph completion and biomedical experiments. The existing link prediction models based on graph neural networks, such as graph convolution neural networks, often only learn the low-frequency information reflecting the common characteristics of nodes while ignoring the high-frequency information reflecting the differences between nodes when learning node representation, which makes the corresponding link prediction models show over smoothness and poor performance. Focusing on links in complex networks, this paper proposes an edge convolutional graph neural network EdgeConvHiF that fuses high-frequency node information to achieve the representation learning of links so that link prediction can be realized by implementing the classification of links. EdgeConvHiF can also be employed as a baseline, and extensive experiments on real-world benchmarks validate that EdgeConvHiF not only has high stability but also has more advantages than the existing representative baselines.

Link prediction in social networks has a long history in complex network research area. The formation of links in networks has been approached by scientists from different backgrounds, ranging from physics to computer science. To predict the formation of new links, we consider measures which originate from network science and use them in the place of mass and distance within the formalism of Newton’s Gravitational Law. The attraction force calculated in this way is treated as a proxy for the likelihood of link formation. In particular, we use three different measures of vertex centrality as mass, and 13 dissimilarity measures including shortest path and inverse Katz score in place of distance, leading to over 50 combinations that we evaluate empirically. Combining these through gravitational law allows us to couple popularity with similarity, two important characteristics for link prediction in social networks. Performance of our predictors is evaluated using Area Under the Precision–Recall Curve (AUC) for seven different real-world network datasets. The experiments demonstrate that this approach tends to outperform the setting in which vertex similarity measures like Katz are used on their own. Our approach also gives us the opportunity to combine network’s global and local properties for predicting future or missing links. Our study shows that the use of the physical law which combines node importance with measures quantifying how distant the nodes are, is a promising research direction in social link prediction.

This chapter presents the problem of link prediction in complex networks. It provides general description, formal definition of the problem and applications. It gives a state-of-art of various existing link prediction approaches concentrating more on topological approaches. It presents the main challenges of link prediction task in real networks. There is description of our new link prediction approach based on supervised rank aggregation and our attempts to deal with two of the challenges to improve the prediction results. One approach is to extend the set of attributes describing an example (pair of nodes) calculated in a multiplex network that includes the target network. Multiplex networks have a layered structure, each layer having different kinds of links between same sets of nodes. The second way is to use community information for sampling of examples to deal with the problem of class imbalance. All experiments have been conducted on real networks extracted from well-known DBLP bibliographic database.

Link prediction in online social networks is useful in numerous applications, mainly for recommendation. Recently, different approaches have considered friendship groups information for increasing the link prediction accuracy. Nevertheless, these approaches do not consider the different roles that common neighbors may play in the different overlapping groups that they belong to. In this paper, we propose a new approach that uses overlapping groups structural information for building a naive Bayes model. From this proposal, we show three different measures derived from the common neighbors. We perform experiments for both unsupervised and supervised link prediction strategies considering the link imbalance problem. We compare sixteen measures in four well-known online social networks: Flickr, LiveJournal, Orkut and Youtube. Results show that our proposals help to improve the link prediction accuracy.