Link Prediction Approach Research Articles

Graph-based machine learning model for weight prediction in protein–protein networks

Proteins interact with each other in complex ways to perform significant biological functions. These interactions, known as protein–protein interactions (PPIs), can be depicted as a graph where proteins are nodes and their interactions are edges. The development of high-throughput experimental technologies allows for the generation of numerous data which permits increasing the sophistication of PPI models. However, despite significant progress, current PPI networks remain incomplete. Discovering missing interactions through experimental techniques can be costly, time-consuming, and challenging. Therefore, computational approaches have emerged as valuable tools for predicting missing interactions. In PPI networks, a graph is usually used to model the interactions between proteins. An edge between two proteins indicates a known interaction, while the absence of an edge means the interaction is not known or missed. However, this binary representation overlooks the reliability of known interactions when predicting new ones. To address this challenge, we propose a novel approach for link prediction in weighted protein–protein networks, where interaction weights denote confidence scores. By leveraging data from the yeast Saccharomyces cerevisiae obtained from the STRING database, we introduce a new model that combines similarity-based algorithms and aggregated confidence score weights for accurate link prediction purposes. Our model significantly improves prediction accuracy, surpassing traditional approaches in terms of Mean Absolute Error, Mean Relative Absolute Error, and Root Mean Square Error. Our proposed approach holds the potential for improved accuracy in predicting PPIs, which is crucial for better understanding the underlying biological processes.

SFGCN: Synergetic fusion-based graph convolutional networks approach for link prediction in social networks

Accurate Link Prediction (LP) in Social Networks (SNs) is crucial for various practical applications, such as recommendation systems and network security. However, traditional techniques often struggle to capture the intricate and multidimensional nature of these networks. This paper presents a novel approach, the Synergetic Fusion-based Graph Convolutional Networks (SFGCN), designed to enhance LP accuracy in SNs. The SFGCN model utilizes a fusion architecture that combines structural features and other attribute data through early, intermediate, and late fusion mechanisms to create improved node and edge representations. We thoroughly evaluate our SFGCN model on seven real-world datasets, encompassing citation networks, co-purchase networks, and academic publication domains. The results demonstrate its superiority over baseline GCN architectures and other selected LP methods, achieving a 6.88 % improvement in accuracy. The experiments show that our model captures the complex interactions and dependencies within SNs, providing a comprehensive understanding of their underlying dynamics. The approach mentioned can be effectively applied in the domain of SN analysis to enhance the accuracy of LP results. This method not only improves the precision of predictions but also enhances the adaptability of the model in diverse SN scenarios.

Network link prediction via deep learning method: A comparative analysis with traditional methods

In the domain of data-centric networks, Link Prediction (LP) is instrumental in discerning potential or absent connections among entities within complex networks. By employing graph data structures, LP techniques enable a detailed analysis of entity interactions across varied sectors, contributing significantly to overcoming challenges in data filtering and integrity restoration, primarily when the network does not provide embedded data. Although LP methods are widely applicable, especially in recommender systems, their efficacy in current social networks needs to be thoroughly investigated. This study introduces an innovative LP approach using Deep Neural Networks (DNNs). We compare our method against a comprehensive set of established techniques, including traditional score-based methods, classical baselines, and recent deep learning approaches like Graph Neural Networks (GNNs). Our DNN-based solution incorporates a robust feature extraction process and a binary classifier, optimized for accurate prediction of missing links within networks. We performed extensive experimental evaluations on diverse datasets, including co-authorship networks, e-commerce, and social media networks. The study encompasses a comparative analysis with traditional LP techniques, namely Common Neighbors, Resource Allocation Index, Jaccard’s Coefficient, and Adamic/Adar Index, as well as other selected baseline and deep-learning methods. Our findings demonstrate that the DNN-based approach significantly enhances predictive accuracy, outperforming the conventional baseline methods in link prediction.

Scientific paper recommender system using deep learning and link prediction in citation network

Today, the number of published scientific articles is increasing day by day, and this has made the process of searching for articles more difficult. The need to provide specific recommender systems (RSs) for suggesting scientific articles is strongly felt in this situation. Because searching for articles based only on matching the titles or content of other articles is not an efficient process. In this research, the combination of two content analysis and citation network is used to design an RS for scientific articles (RECSA). In RECSA, natural language processing and deep learning techniques are used to process the titles and extract the content attributes of the articles. For this purpose, first, the titles of the articles are pre-processed, and by using the Term Frequency Inverse Document Frequency (TF-IDF) criterion, the importance of each word in the title is estimated. Then the dimensions of the obtained attributes are reduced by using a convolutional neural network (CNN). Then, by using the cosine similarity criterion, the content similarity matrix of the articles is calculated based on the attribute vectors. Also, the link prediction approach is used to analyze the connections of scientific articles' citation network. Finally, in the third step of RECSA, the two similarity matrices calculated in the previous steps are combined using an influence coefficient parameter to obtain the final similarity matrix, and the recommendation operation is based on the highest similarity value. The efficiency of RECSA has been evaluated from different aspects and the results have been compared with previous works. According to the results, utilizing the combination of TF-IDF and CNN for analyzing content-based features, leads to at least 0.32 % improvement in terms of precision compared to previous works. Also, by integrating citation and content-based data, the precision of first suggestion in RECSA would be 99.01 % which indicates the minimum improvement of 0.9 % compared to compared methods. The results show that by using RECSA, the recommendation can be done with higher accuracy and efficiency.

The RDF2vec family of knowledge graph embedding methods

Knowledge graph embeddings represent a group of machine learning techniques which project entities and relations of a knowledge graph to continuous vector spaces. RDF2vec is a scalable embedding approach rooted in the combination of random walks with a language model. It has been successfully used in various applications. Recently, multiple variants to the RDF2vec approach have been proposed, introducing variations both on the walk generation and on the language modeling side. The combination of those different approaches has lead to an increasing family of RDF2vec variants. In this paper, we evaluate a total of twelve RDF2vec variants on a comprehensive set of benchmark models, and compare them to seven existing knowledge graph embedding methods from the family of link prediction approaches. Besides the established GEval benchmark introducing various downstream machine learning tasks on the DBpedia knowledge graph, we also use the new DLCC (Description Logic Class Constructors) benchmark consisting of two gold standards, one based on DBpedia, and one based on synthetically generated graphs. The latter allows for analyzing which ontological patterns in a knowledge graph can actually be learned by different embedding. With this evaluation, we observe that certain tailored RDF2vec variants can lead to improved performance on different downstream tasks, given the nature of the underlying problem, and that they, in particular, have a different behavior in modeling similarity and relatedness. The findings can be used to provide guidance in selecting a particular RDF2vec method for a given task.

Node2Vec and Machine Learning: A Powerful Duo for Link Prediction in Social Network

Link prediction in social networks is a challenging task that attempts to uncover hidden linkages and forecast future connections. The link prediction problem is addressed in this research article by utilizing the capabilities of Node2Vec and machine learning algorithms. To learn high-dimensional node representations that capture both local and global network structures, the Node2Vec technique is used. Then, in order to forecast potential connections, these node embedding’s are put into various machine learning models. Two real-world social network datasets are used to test the suggested methodology, and the findings show a considerable improvement in link prediction accuracy. It achieves a deeper comprehension of the hidden relationships in social networks by fusing the semantic richness of Node2Vec embedding’s with the predictive powers of machine learning methods. The results of this study extend link prediction approaches in social networks by revealing hidden ties and providing insightful predictions for upcoming connections. The suggested method indicates the potential for real-world applications in a number of fields, including recommender systems, targeted advertising, and social influence studies.

SEGCECO: Subgraph Embedding of Gene expression matrix for prediction of CEll-cell COmmunication.

Recent advances in single-cell RNA sequencing technology have eased analyses of signaling networks of cells. Recently, cell-cell interaction has been studied based on various link prediction approaches on graph-structured data. These approaches have assumptions about the likelihood of node interaction, thus showing high performance for only some specific networks. Subgraph-based methods have solved this problem and outperformed other approaches by extracting local subgraphs from a given network. In this work, we present a novel method, called Subgraph Embedding of Gene expression matrix for prediction of CEll-cell COmmunication (SEGCECO), which uses an attributed graph convolutional neural network to predict cell-cell communication from single-cell RNA-seq data. SEGCECO captures the latent and explicit attributes of undirected, attributed graphs constructed from the gene expression profile of individual cells. High-dimensional and sparse single-cell RNA-seq data make converting the data into a graphical format a daunting task. We successfully overcome this limitation by applying SoptSC, a similarity-based optimization method in which the cell-cell communication network is built using a cell-cell similarity matrix which is learned from gene expression data. We performed experiments on six datasets extracted from the human and mouse pancreas tissue. Our comparative analysis shows that SEGCECO outperforms latent feature-based approaches, and the state-of-the-art method for link prediction, WLNM, with 0.99 ROC and 99% prediction accuracy. The datasets can be found at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE84133 and the code is publicly available at Github https://github.com/sheenahora/SEGCECO and Code Ocean https://codeocean.com/capsule/8244724/tree.

Dual-Path Graph Neural Network with Adaptive Auxiliary Module for Link Prediction.

Link prediction, which has important applications in many fields, predicts the possibility of the link between two nodes in a graph. Link prediction based on Graph Neural Network (GNN) obtains node representation and graph structure through GNN, which has attracted a growing amount of attention recently. However, the existing GNN-based link prediction approaches possess some shortcomings. On the one hand, because a graph contains different types of nodes, it leads to a great challenge for aggregating information and learning node representation from its neighbor nodes. On the other hand, the attention mechanism has been an effect instrument for enhancing the link prediction performance. However, the traditional attention mechanism is always monotonic for query nodes, which limits its influence on link prediction. To address these two problems, a Dual-Path Graph Neural Network (DPGNN) for link prediction is proposed in this study. First, we propose a novel Local Random Features Augmentation for Graph Convolution Network as a baseline of one path. Meanwhile, Graph Attention Network version 2 based on dynamic attention mechanism is adopted as a baseline of the other path. And then, we capture more meaningful node representation and more accurate link features by concatenating the information of these two paths. In addition, we propose an adaptive auxiliary module for better balancing the weight of auxiliary tasks, which brings more benefit to link prediction. Finally, extensive experiments verify the effectiveness and superiority of our proposed DPGNN for link prediction.

A Weighted Symmetric Graph Embedding Approach for Link Prediction in Undirected Graphs.

Link prediction is an important task in social network analysis and mining because of its various applications. A large number of link prediction methods have been proposed. Among them, the deep learning-based embedding methods exhibit excellent performance, which encodes each node and edge as an embedding vector, enabling easy integration with traditional machine learning algorithms. However, there still remain some unsolved problems for this kind of methods, especially in the steps of node embedding and edge embedding. First, they either share exactly the same weight among all neighbors or assign a completely different weight to each node to obtain the node embedding. Second, they can hardly keep the symmetry of edge embeddings obtained from node representations by direct concatenation or other binary operations such as averaging and Hadamard product. In order to solve these problems, we propose a weighted symmetric graph embedding approach for link prediction. In node embedding, the proposed approach aggregates neighbors in different orders with different aggregating weights. In edge embedding, the proposed approach bidirectionally concatenates node pairs both forwardly and backwardly to guarantee the symmetry of edge representations while preserving local structural information. The experimental results show that our proposed approach can better predict network links, outperforming the state-of-the-art methods. The appropriate aggregating weight assignment and the bidirectional concatenation enable us to learn more accurate and symmetric edge representations for link prediction.

A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific Literature

This study presents a novel approach that synergizes community detection algorithms with various Graph Neural Network (GNN) models to bolster link prediction in scientific literature networks. By integrating the Louvain community detection algorithm into our GNN frameworks, we consistently enhanced the performance across all models tested. For example, integrating the Louvain model with the GAT model resulted in an AUC score increase from 0.777 to 0.823, exemplifying the typical improvements observed. Similar gains were noted when the Louvain model was paired with other GNN architectures, confirming the robustness and effectiveness of incorporating community-level insights. This consistent increase in performance—reflected in our extensive experimentation on bipartite graphs of scientific collaborations and citations—highlights the synergistic potential of combining community detection with GNNs to overcome common link prediction challenges such as scalability and resolution limits. Our findings advocate for the integration of community structures as a significant step forward in the predictive accuracy of network science models, offering a comprehensive understanding of scientific collaboration patterns through the lens of advanced machine learning techniques.

MADLINK: Attentive multihop and entity descriptions for link prediction in knowledge graphs

Knowledge Graphs (KGs) comprise of interlinked information in the form of entities and relations between them in a particular domain and provide the backbone for many applications. However, the KGs are often incomplete as the links between the entities are missing. Link Prediction is the task of predicting these missing links in a KG based on the existing links. Recent years have witnessed many studies on link prediction using KG embeddings which is one of the mainstream tasks in KG completion. To do so, most of the existing methods learn the latent representation of the entities and relations whereas only a few of them consider contextual information as well as the textual descriptions of the entities. This paper introduces an attentive encoder-decoder based link prediction approach considering both structural information of the KG and the textual entity descriptions. Random walk based path selection method is used to encapsulate the contextual information of an entity in a KG. The model explores a bidirectional Gated Recurrent Unit (GRU) based encoder-decoder to learn the representation of the paths whereas SBERT is used to generate the representation of the entity descriptions. The proposed approach outperforms most of the state-of-the-art models and achieves comparable results with the rest when evaluated with FB15K, FB15K-237, WN18, WN18RR, and YAGO3-10 datasets.

BehaviorNet: A Fine-grained Behavior-aware Network for Dynamic Link Prediction

Dynamic link prediction has become a trending research subject because of its wide applications in the web, sociology, transportation, and bioinformatics. Currently, the prevailing approach for dynamic link prediction is based on graph neural networks, in which graph representation learning is the key to perform dynamic link prediction tasks. However, there are still great challenges because the structure of graphs evolves over time. A common approach is to represent a dynamic graph as a collection of discrete snapshots, in which information over a period is aggregated through summation or averaging. This way results in some fine-grained time-related information loss, which further leads to a certain degree of performance degradation. We conjecture that such fine-grained information is vital because it implies specific behavior patterns of nodes and edges in a snapshot. To verify this conjecture, we propose a novel fine-grained behavior-aware network (BehaviorNet) for dynamic network link prediction. Specifically, BehaviorNet adapts a transformer-based graph convolution network to capture the latent structural representations of nodes by adding edge behaviors as an additional attribute of edges. GRU is applied to learn the temporal features of given snapshots of a dynamic network by utilizing node behaviors as auxiliary information. Extensive experiments are conducted on several real-world dynamic graph datasets, and the results show significant performance gains for BehaviorNet over several state-of-the-art (SOTA) discrete dynamic link prediction baselines. Ablation study validates the effectiveness of modeling fine-grained edge and node behaviors.

Distance-Aware Learning for Inductive Link Prediction on Temporal Networks.

Inductive link prediction on temporal networks aims to predict the future links associated with node(s) unseen in the historical timestamps. Existing methods generate the predictions mainly by learning node representation from the node/edge attributes as well as the network dynamics or by measuring the distance between nodes on the temporal network structure. However, the attribute information is unavailable in many realistic applications and the structure-aware methods highly rely on nodes' common neighbors, which are difficult to accurately detect, especially in sparse temporal networks. Thus, we propose a distance-aware learning (DEAL) approach for inductive link prediction on temporal networks. Specifically, we first design an adaptive sampling method to extract temporal adaptive walks for nodes, increasing the probability of including the common neighbors between nodes. Then, we design a dual-channel distance measuring component, which simultaneously measures the distance between nodes in the embedding space and on the dynamic graph structure for predicting future inductive edges. Extensive experiments are conducted on three public temporal network datasets, i.e., MathOverflow, AskUbuntu, and StackOverflow. The experimental results validate the superiority of DEAL over the state-of-the-art baselines in terms of accuracy, area under the ROC curve (AUC), and average precision (AP), where the improvements are especially obvious in scenarios with only limited data.

A Novel Similarity-Based Link Prediction Approach for Transaction Networks

A network consists of nodes and links, which represent components of a system and interactions between them, respectively. An example of networks is transaction networks, in which nodes and links represent firms and transactions, respectively. Link prediction in transaction networks is an important problem, which aims to estimate the likelihood of a transaction between two firms. It can be used to predict missing link information between firms to gain fuller knowledge as transaction information is not easily accessible between firms. In addition, firms can use it to predict future transactions as transactions evolve over time for various reasons such as a shift in customer demand, resource availability, etc. Many link prediction methods have been proposed for networks. However, to the best of our knowledge, there is no existing link prediction method for transaction networks. Existing methods are not suitable for transaction networks as they assume homophily, the tendency of individuals to associate with similar others, which may not be true in transaction networks. In addition, they do not consider the hierarchy structure exhibited in transaction networks. In this article, we propose a new similarity score for transaction networks that account for multiple, temporal, and directed transactions. We then propose a link prediction procedure based on the proposed similarity score to predict new transactions in transaction networks, which avoids the homophily assumption and exploits the hierarchical structure of transaction networks. The proposed method is tested on real-world transaction networks and yields better area under the receiver operating characteristic curve compared to existing methods.

A novel and precise approach for similarity-based link prediction in diverse networks

A novel and precise approach for similarity-based link prediction in diverse networks

A Novel Hybrid Approach for Similarity-Based Link Prediction in Complex Networks

Link prediction in complex networks is the challenging task of predicting missing or future connections between nodes. Complex networks, such as social networks, biological networks, and online recommendation systems, are often incomplete, with unknown or unestablished relationships between nodes. Link prediction algorithms fill in these missing links by leveraging the existing network structure and properties. By analyzing network patterns, connectivity, and characteristics, these algorithms can predict the likelihood of future connections, enabling applications such as recommender systems, network analysis, and understanding the dynamics of complex systems. Link prediction is a crucial task for providing relevant recommendations in e-commerce recommender systems. However, it is challenging due to the sparsity of user-item interaction data and the dynamic nature of user preferences. In this paper, we propose a novel hybrid link prediction algorithm that combines the Jaccard Coefficient Similarity Index, Adamic Adar Index, and MapSim Similarity based Index methods. Our algorithm leverages the complementary strengths of each individual method to improve the overall prediction accuracy. The Jaccard Coefficient Similarity Index measures the similarity between two users or items based on the number of shared items or users. The Adamic Adar Index considers the common neighbors between two users or items to predict the link probability. The MapSim Similarity based Index method incorporates the geographic location of users and items to predict the link probability. We evaluate our proposed hybrid algorithm on two real-world e-commerce datasets, and the results show that it outperforms several state-of-the-art link prediction algorithms in terms of accuracy and precision.

Link prediction approach to recommender systems

Link prediction approach to recommender systems

Deep Autoencoder-like non-negative matrix factorization with graph regularized for link prediction in dynamic networks

Link prediction in dynamic(temporal) networks refers to predicting future edges by analyzing the available network information. Among the existing temporal link prediction approaches, non-negative matrix factorization(NMF) is a kind of competitive algorithm and has attracted extensive attention. However, traditional NMF-based prediction methods are shallow methods and cannot fully mine the dynamic network, which may lead to a decrease in performance of algorithms. To overcome these shortcomings, inspired by deep Autoencoder, we propose two novel deep Autoencoder-like NMF with graph regularized prediction methods for dynamic networks. By fusing encoder component with deep structure into deep NMF model, our algorithms can sufficiently exploit the complex hierarchical information hidden in dynamic networks. To further extract the abundant information hidden in dynamic networks, graph regularization and PageRank are utilized to exploit the local and global topology information of each snapshot, respectively. By jointly optimizing them in deep Autoencoder-like NMF model, our model is able to preserve the local and global information hidden in dynamic networks, simultaneously. Moreover, an effective alternating iterative method with convergence guarantee is developed for minimizing the established model. Finally, we test our proposed prediction methods on several synthetic and real world datasets to demonstrate that our approaches outperform the state-of-the-art prediction approaches.

Discrete log anomaly detection: A novel time-aware graph-based link prediction approach

With the implementation of online-service information systems, it is important to detect system anomalies. Logs, serving as the system runtime information, are the key resources to understand system statuses. The existing automatic log anomaly detection approaches focused on the temporal features deriving from sequential nature of logs/events, which can be suitable for limited-sized information systems with homogeneous structure. However, with increasing complexity of systems, the time-aware relationships among discrete logs/events become non-trivial features. Different from the previous works, a novel framework for log anomaly detection is proposed from the perspective of link prediction. First, a temporal event graph is constructed to model the time-aware relationships between events, which is derived from discrete event sequences and possesses the evolutionary properties of sequential events. Second, we pre-train a graph convolutional neural network by using graph contrastive learning to capture local topological features. Third, a temporal convolutional network is used to learn the temporal features. Finally, based on generative adversarial network, link prediction is implemented by generating the next moment event graph, which also is the basis for anomaly detection. Experiments are conducted on public datasets to verify the validity of the model, and superior results are achieved compared to the state-of-the-art methods.

A hybrid clustering approach for link prediction in heterogeneous information networks

A hybrid clustering approach for link prediction in heterogeneous information networks