HuGE: An Entropy-driven Approach to Efficient and Scalable Graph Embeddings

Perturbation analysis on PCA plus graph embedding methods and PCA plus exponential graph embedding methods

GEHGAN[formula omitted] CircRNA–disease association prediction via graph embedding and heterogeneous graph attention network

Emerging technologies for drug repurposing: Harnessing the potential of text and graph embedding approaches

The study of protein–protein interaction and the determination of protein functions are important parts of proteomics. Computational methods are used to study the similarity between proteins based on Gene Ontology (GO) to explore their functions and possible interactions. GO is a series of standardized terms that describe gene products from molecular functions, biological processes, and cell components. Previous studies on assessing the similarity of GO terms were primarily based on Information Content (IC) between GO terms to measure the similarity of proteins. However, these methods tend to ignore the structural information between GO terms. Therefore, considering the structural information of GO terms, we systematically analyze the performance of the GO graph and GO Annotation (GOA) graph in calculating the similarity of proteins using different graph embedding methods. When applied to the actual Human and Yeast datasets, the feature vectors of GO terms and proteins are learned based on different graph embedding methods. To measure the similarity of the proteins annotated by different GO numbers, we used Dynamic Time Warping (DTW) and cosine to calculate protein similarity in GO graph and GOA graph, respectively. Link prediction experiments were then performed to evaluate the reliability of protein similarity networks constructed by different methods. It is shown that graph embedding methods have obvious advantages over the traditional IC-based methods. We found that random walk graph embedding methods, in particular, showed excellent performance in calculating the similarity of proteins. By comparing link prediction experiment results from GO(DTW) and GOA(cosine) methods, it is shown that GO(DTW) features provide highly effective information for analyzing the similarity among proteins.

Graph embedding techniques have gained increasing attention for their ability to encode the complex structural information of networks into low-dimensional vectors. Existing graph embedding methods have achieved considerable success in various applications. However, these methods have limitations in capturing global graph topology information and fail to provide insights into the underlying mechanisms of network function. In this paper, we propose IsoGloVe, a count-based method that encodes graph topology into vectors using the co-occurrence statistics of fixed-size routes in random walks. IsoGloVe calculates the final embeddings based on the geodesic distances of the node’s neighbors on a manifold. This representation in geodesic space allows for the analysis of node interactions and contributes to a better understanding of complex network structure and function. The performance of IsoGloVe is evaluated on various protein-protein interactions (PPI) using graph reconstruction, node classification, and visualization. The findings reveal that IsoGloVe surpasses other comparable methods with a 30% increase in MAP for graph reconstruction and a 25% increase in model scores for node classification in the Yeast PPI network. In addition, IsoGloVe demonstrated a 6.9% increase in MAP for graph reconstruction on the Human PPI network.

The discovery of gene-disease associations is important for preventing, diagnosing, and treating diseases. In this paper, we propose two heterogeneous network-based methods that enhance gene-disease association prediction by using graph embedding and ensemble learning, abbreviated as 'HNEEM' and 'HNEEM-PLUS'. We integrate gene-disease associations, gene-chemical associations, gene-gene associations and disease-chemical associations to construct a heterogeneous network, and adopt six graph embedding methods respectively to learn the representative vectors of genes and diseases from the network. We build individual prediction models using each graph embedding representation and random forest, and then combine them by average scoring to construct the ensemble model HNEEM. To increase the diversity of base predictors, we further introduce the multilayer perceptron as an additional classifier and generate more base predictors, and thus propose an extended method named 'HNEEM-PLUS'. Computational experiments show that HNEEM has better results than individual methods and HNEEM-PLUS makes more improvement than HNEEM.

In recent years, the analysis of human interaction data has led to the rapid development of graph embedding methods. For link-based classification problems, topological information typically appears in various machine learning tasks in the form of embedded vectors or convolution kernels. This paper introduces a Bayesian graph embedding model for such problems, integrating network reconstruction, link prediction, and behavior prediction into a unified framework. Unlike the existing graph embedding methods, this model does not embed the topology of nodes or links into a low-dimensional space but sorts the probabilities of upcoming links and fuses the information of node topology and data domain via sorting. The new model integrates supervised transaction predictors with unsupervised link prediction models, summarizing local and global topological information. The experimental results on a financial trading dataset and a retweet network dataset demonstrate that the proposed feature fusion model outperforms the tested benchmarked machine learning algorithms in precision, recall, and F1-measure. The proposed learning structure has a fundamental methodological contribution and can be extended and applied to various link-based classification problems in different fields.

Link prediction is to calculate the probability of a potential link between a pair of unlinked nodes in the future. It has significance value in both theoretical and practical. The similarity of two nodes in the networks is an essential factor to determine the probability of a potential link between them. One of the important methods with the similarity of two nodes is to consider common neighbors of two nodes. However, the number of common neighbors only describes a kind of quantitative relationship without taking into account the topology of given networks and the information of local structure which consist of a pair of nodes and their common neighbors. Therefore, we introduce the concept of the degrees of nodes and the idea of community structure and propose a new similarity index, namely, local affinity structure(LAS). The LAS method describes the closeness of a pair of nodes and their common neighbors. We evaluated LAS on twelve different networks compared with other three similarity based indexes which consider the degree of nodes. From the experimental results, our method shows obvious superiority in improving the accuracy of link prediction.

ExEm: Expert embedding using dominating set theory with deep learning approaches

Social network analysis has recently attracted lots of attention among researchers due to its wide applicability in capturing social interactions. Link prediction, related to the likelihood of having a link between two nodes of the network that are not connected, is a key problem in social network analysis. Many methods have been proposed to solve the problem. Among these methods, similarity-based methods exhibit good efficiency by considering the network structure and using as a fundamental criterion the number of common neighbours between two nodes to establish structural similarity. High structural similarity may suggest that a link between two nodes is likely to appear. However, as shown in the paper, the number of common neighbours may not be always sufficient to provide comprehensive information about structural similarity between a pair of nodes. To address this, a neighbourhood vector is first specified for each node. Then, a novel measure is proposed to determine the similarity of each pair of nodes based on the number of common neighbours and correlation between the neighbourhood vectors of the nodes Experimental results, on a range of different real-world networks, suggest that the proposed method results in higher accuracy than other state-of-the-art similarity-based methods for link prediction.

In this paper, we present a model which incorporates biomedical knowledge graph, graph embedding and deep learning methods for literature-based discovery. Firstly, the relations between entities are extracted from biomedical abstracts and then a knowledge graph is constructed by using these obtained relations. Secondly, the graph embedding technologies are applied to convert the entities and relations in the knowledge graph into a low-dimensional vector space. Thirdly, a bidirectional Long Short-Term Memory network is trained based on the entity associations represented by the pre-trained graph embeddings. Finally, the learned model is used for open and closed literature-based discovery tasks. The experimental results show that our method could not only effectively discover hidden associations between entities, but also reveal the corresponding mechanism of interactions. It suggests that incorporating knowledge graph and deep learning methods is an effective way for capturing the underlying complex associations between entities hidden in the literature.

With the development and popularity of social networks, many human beings prefer to share their experiences on these networks. There are various methods proposed by the researcher which utilized user-generated content in the location-based social networks (LBSN) and recommend locations to users. However, there is a high sparsity in the user check-in information makes it tough to recommend the appropriate and accurate location to the user. To fix this issue, we put forward a proposal as a framework which utilizes a wide range of information available in these networks, each of which has its own type and provides appropriate recommendation. For this purpose, we encode the information as a number of entities and its attributes in the form of a heterogeneous graph, then graph embedding methods are used to embed all nodes in unified semantic representation space. As a result, we are able to model relations between users and venues in an efficient way and ameliorate the accuracy of the proposed method that recommends a place to a user. Our method is implemented and evaluated using Foursquare dataset, and the evaluation results depict that our work, boost performance in terms of precision, recall, and f-measure compared to the baseline work.

Graph representation learning is a fundamental task in various applications that strives to learn low-dimensional embeddings for nodes that can preserve graph topology information. However, many existing methods focus on static graphs while ignoring evolving graph patterns. Inspired by the success of graph convolutional networks(GCNs) in static graph embedding, we propose a novel k-core based temporal graph convolutional network, the CTGCN, to learn node representations for dynamic graphs. In contrast to previous dynamic graph embedding methods, CTGCN can preserve both local connective proximity and global structural similarity while simultaneously capturing graph dynamics. In the proposed framework, the traditional graph convolution is generalized into two phases, feature transformation and feature aggregation, which gives the CTGCN more flexibility and enables the CTGCN to learn connective and structural information under the same framework. Experimental results on 7 real-world graphs demonstrate that the CTGCN outperforms existing state-of-the-art graph embedding methods in several tasks, including link prediction and structural role classification. The source code of this work can be obtained from <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/jhljx/CTGCN</uri> .

Graph embedding aims to learn the low-dimensional representation of nodes in the network, which has been paid more and more attention in many graph-based tasks recently. Graph Convolution Network (GCN) is a typical deep semisupervised graph embedding model, which can acquire node representation from the complex network. However, GCN usually needs to use a lot of labeled data and additional expressive features in the graph embedding learning process, so the model cannot be effectively applied to undirected graphs with only network structure information. In this paper, we propose a novel unsupervised graph embedding method via hierarchical graph convolution network (HGCN). Firstly, HGCN builds the initial node embedding and pseudo-labels for the undirected graphs, and then further uses GCNs to learn the node embedding and update labels, finally combines HGCN output representation with the initial embedding to get the graph embedding. Furthermore, we improve the model to match the different undirected networks according to the number of network node label types. Comprehensive experiments demonstrate that our proposed HGCN and HGCN∗ can significantly enhance the performance of the node classification task.

Hyperspectral data are the spectral response of landcovers from different spectral bands and different band sets can be treated as different views of landcovers, which may contain different structure information. Therefore, multiview graphs ensemble-based graph embedding is proposed to promote the performance of graph embedding for hyperspectral image classification. By integrating multiview graphs, more affluent and more accurate structure information can be utilized in graph embedding to achieve better results than traditional graph embedding methods. In addition, the multiview graphs ensemble-based graph embedding can be treated as a framework to be extended to different graph-based methods. Experimental results demonstrate that the proposed method can improve the performance of traditional graph embedding methods significantly.