Heterogeneous network representation learning based on role feature extraction

Aiming at the problem of 5G multimedia heterogeneous multimodal network representation learning, this paper proposes a collaborative multimodal heterogeneous network representation learning method based on attention mechanism. This method learns different representations for nodes based on heterogeneous network structure information and multimodal content and designs an attention mechanism to learn weights for different representations to fuse them to obtain robust node representations. Combining the general process of exploring the college physical education model and the characteristics of the multimedia network classroom environment, this article constructs the process of exploring the college physical education teaching model of the multimedia network classroom. Through the research and practice of the inquiry college physical education teaching model in the multimedia network classroom, it is verified that the implementation of the inquiry college physical education teaching in the multimedia network classroom can effectively influence and increase the students’ interest in learning and stimulate the students’ inner learning motivation. Through the guidance and training of teachers, a variety of disciplines can be used to carry out college physical education in multimedia network classrooms, so that the integration between courses can be truly realized, with the aim that all courses can share the excellent results brought by the development of modern education technology. More educators understand, accept, and participate in the practice of college physical education based on multimedia network classrooms and better serve the education of college physical education. The construction of the college physical education evaluation system should be combined with the characteristics of the 5G multimedia network era. The evaluation process includes data collection, data analysis, result output, and result feedback. Each link is an indispensable part of the college physical education evaluation process. Based on the relevant knowledge of the 5G multimedia network, the evaluation indicators determined in this study can basically reflect the various elements of the physical education process in colleges and universities. The distribution of index weight coefficients is more scientific and reasonable. Compared with the current system, the college physical education evaluation system constructed by exploration has a certain degree of objectivity and scientificity. Therefore, it is feasible to apply the 5G multimedia network to the evaluation of college physical education.

Identifying influential nodes in complex networks is crucial for applications like information diffusion, rumor propagation, and epidemic spreading. Existing methods often assume uniform importance among neighbor nodes or fail to account for the structural and semantic diversity of relationships in heterogeneous networks. This leads to suboptimal identification of influential nodes, particularly in complex, attribute-rich networks. To address these shortcomings, a meta-path embedding-based graph attention network model is proposed, namely MEGA. MEGA is utilized to identify influential nodes in heterogeneous networks. This paper attempts to identify the influential set of author nodes in academic networks, defined as the set of nodes whose influence maximizes the spread of information. MEGA is described as follows. Firstly, the required meta-paths are defined, and node embeddings are obtained using a meta-path embedding method. Then, the subgraph networks corresponding to each meta-path network are generated based on random walks. Further, the graph attention network is employed to assign different weight values to neighbor nodes within the subgraph networks, indicating the varying influence of nodes on their neighbor nodes. Finally, the influence of nodes in the subgraph network is calculated using entropy, and the influence values from all subgraphs are aggregated to obtain the final influence value of each node. The effectiveness of MEGA is validated using analysis metrics from the independent cascade model. Experimental results demonstrate MEGA exceeds six baseline methods in terms of the influence spread across three datasets.

With the advent of the Internet era, the recommendation system has developed rapidly. Heterogeneous information networks representation learning is widely used in recommendation systems due to its advantages in complex information modeling. Although the performance of the recommendation system has been improved, there are still two shortcomings: 1. There is a lot of noise data in the instances of the meta-path generated by random walks of meta-paths, which will reduce the performance of the recommendation system. 2. Traditional recommendation algorithms fail to make full use of the relevant meta-path information in heterogeneous information networks, which makes the recommendation results lack of interpretability. To solve these problems, we propose a recommendation system based on heterogeneous network representation learning and neural network model. Firstly, use the matrix factorization and the similarity calculation to select the meta-path instances with good quality as the pre-training vectors of the recommendation system. Then, we combine LSTM with Attention mechanism to learn the user, item and meta-path embeddings, and use MLP to make prediction after fusion to jointly improve the recommendation effect. We conducted experiments on Movielens datasets to evaluate the performance of our proposed recommendation.

Due to the cost and complexity of biological experiments, many computational methods have been proposed to predict potential miRNA-disease associations by utilizing known miRNA-disease associations and other related information. However, there are some challenges for these computational methods. First, the relationships between miRNAs and diseases are complex. The computational network should consider the local and global influence of neighborhoods from the network. Furthermore, predicting disease-related miRNAs without any known associations is also very important. This study presents a new computational method that constructs a heterogeneous network composed of a miRNA similarity network, disease similarity network, and known miRNA-disease association network. The miRNA similarity considers the miRNAs and their possible families and clusters. The information of each node in heterogeneous network is obtained by aggregating neighborhood information with graph convolutional networks (GCNs), which can pass the information of a node to its intermediate and distant neighbors. Disease-related miRNAs with no known associations can be predicted with the reconstructed heterogeneous matrix. We apply 5-fold cross-validation, leave-one-disease-out cross-validation, and global and local leave-one-out cross-validation to evaluate our method. The corresponding areas under the curves (AUCs) are 0.9616, 0.9946, 0.9656, and 0.9532, confirming that our approach significantly outperforms the state-of-the-art methods. Case studies show that this approach can effectively predict new diseases without any known miRNAs.

This paper proposes interference-based decode and forward scheme that utilizes relay stations (RSs). In Long-Term-Evolution (LTE-) Advanced, heterogeneous networks in which femto- and picocells are overlaid onto macrocells are extensively discussed. However, interference between macro- and pico(femto)cells arises due to their different transmit power levels. Unlike conventional cooperative transmission schemes, the RS decodes interference in the first transmit timing period and forwards it to the user equipment (UE) in the second period. Moreover, cooperative transmission can be achieved without stopping the transmission from the base station (BS) to UE when forwarding the interference from the RS to the UE by utilizing the fact that signal-to-noise power ratio (SNR) between the RS and UE is much greater than that between the BS and UE. The basic performance of the proposed method is shown based on computer simulation. Moreover, the interference temperature and shadowing effect are measured when considering the coexistence between macro- and femtocells, and the performance of the proposed method is verified using measured shadowing effect.

BackgroundSeveral types of RNA in the cell are usually involved in biological processes with multiple functions. Coding RNAs code for proteins while non-coding RNAs regulate gene expression. Some single-strand RNAs can create a circular shape via the back splicing process and convert into a new type called circular RNA (circRNA). circRNAs are among the essential non-coding RNAs in the cell that involve multiple disorders. One of the critical functions of circRNAs is to regulate the expression of other genes through sponging micro RNAs (miRNAs) in diseases. This mechanism, known as the competing endogenous RNA (ceRNA) hypothesis, and additional information obtained from biological datasets can be used by computational approaches to predict novel associations between disease and circRNAs.ResultsWe applied multiple classifiers to validate the extracted features from the heterogeneous network and selected the most appropriate one based on some evaluation criteria. Then, the XGBoost is utilized in our pipeline to generate a novel approach, called CircWalk, to predict CircRNA-Disease associations. Our results demonstrate that CircWalk has reasonable accuracy and AUC compared with other state-of-the-art algorithms. We also use CircWalk to predict novel circRNAs associated with lung, gastric, and colorectal cancers as a case study. The results show that our approach can accurately detect novel circRNAs related to these diseases.ConclusionsConsidering the ceRNA hypothesis, we integrate multiple resources to construct a heterogeneous network from circRNAs, mRNAs, miRNAs, and diseases. Next, the DeepWalk algorithm is applied to the network to extract feature vectors for circRNAs and diseases. The extracted features are used to learn a classifier and generate a model to predict novel CircRNA-Disease associations. Our approach uses the concept of the ceRNA hypothesis and the miRNA sponge effect of circRNAs to predict their associations with diseases. Our results show that this outlook could help identify CircRNA-Disease associations more accurately.

In recent years, miRNA variation and dysregulation have been found to be closely related to human tumors, and identifying miRNA-disease associations is helpful for understanding the mechanisms of disease or tumor development and is greatly significant for the prognosis, diagnosis, and treatment of human diseases. This article proposes a Bipartite Heterogeneous network link prediction method based on co-neighbor to predict miRNA-disease association (BHCN). According to the structural characteristics of the bipartite network, the concept of bipartite network co-neighbors is proposed, and the co-neighbors were used to represent the probability of association between disease and miRNA. To predict the isolated diseases and the new miRNA based on the association probability expressed by co-neighbors, we utilized the similarity between disease nodes and the similarity between miRNA nodes in heterogeneous networks to represent the association probability between disease and miRNA. The model's predictive performance was evaluated by the leave-one-out cross validation (LOOCV) on different datasets. The AUC value of BHCN on the gold benchmark dataset was 0.7973, and the AUC obtained on the prediction dataset was 0.9349, which was better than that of the classic global algorithm. In this case study, we conducted predictive studies on breast neoplasms and colon neoplasms. Most of the top 50 predicted results were confirmed by three databases, namely, HMDD, miR2disease, and dbDEMC, with accuracy rates of 96 and 82%. In addition, BHCN can be used for predicting isolated diseases (without any known associated diseases) and new miRNAs (without any known associated miRNAs). In the isolated disease case study, the top 50 of breast neoplasm and colon neoplasm potentials associated with miRNAs predicted an accuracy of 100 and 96%, respectively, thereby demonstrating the favorable predictive power of BHCN for potentially relevant miRNAs.

In this paper, we develop an effective inter-cell interference coordination (ICIC) scheme for co-channel interference in downlink orthogonal frequency division multiple access (OFDMA) networks through cognitive sensing performed by subnet nodes in heterogeneous network (Het-Net). The more co-channel interference is detected and avoided, the more power is saved for both macro BS and subnet nodes. The strategy framework of the cognitive critical ratio and the number of subnet nodes is set up for interference management aiming at maximizing net saving power for the whole system. The framework is modeled as multiple objective non-linear programming (MONLP), employing parallel vector evaluated particle swarm optimization algorithm (VEPSO) to obtain the global optimum solution. Utilizing dynamic traffic loads, we could figure out the optimal deployment of low-power BSs. Finally, the practical implementation in Het-Net for long term evolution advanced (LTE-A) is designed. The numerical evaluation and system simulation results demonstrate the applicability and effectiveness of the proposed interference management framework.

One of the most promising frameworks to handle mobility management in wireless heterogeneous networks is the Media Independent Handover (MIH) standard. Among the services MIH is providing to achieve efficient mobility management, Information Services allow data exchanging between heterogeneous network nodes. In this paper, we propose an implementation of this Media Independent Information Services (MIIS) on Network Simulator 2 (NS2). With this implementation, new mobility and handoff scenarios can be realized. As an example, we study the case where a mobile node gathers relevant data of nearby networks through only one interface while keeping the others disconnected in order to save battery power. Results show that our implementation is fully functional and demonstrate how useful can be MIIS for mobility management.

To predict the Quality of Service at a node in heterogeneous networks of line‐of‐sight, terrestrial, microwave links requires knowledge of the spatial and temporal statistics of rain over scales of a few meters to tens or hundreds of kilometers, and over temporal periods as short as 1 s. Meteorological radar databases provide rain rate maps over areas with a spatial resolution as fine as a few hundred meters and a sampling period of 2 to 15 min. Such two‐dimensional, rain rate map time series would have wide application in the simulation of rain scatter and attenuation of arbitrary millimeter‐wave radio networks, if the sampling period were considerably shorter, i.e., of the order of 10 s or less, and the integration volumes smaller. This paper investigates a stochastic‐numerical method to interpolate and downscale rain rate field time series to shorter sampling periods and smaller spatial integration areas, while conserving the measured and expected statistics. A series of radar derived rain maps, with a 10 min sample period, are interpolated to 10 s. The statistics of the interpolated‐downscaled data are compared to fine‐scale rain data, i.e., 10 s rain gauge data and radar data with a 300‐m resolution. The interpolated rain map time series is used to predict the fade duration statistics of a microwave link, and these are compared to a published and ITU‐R model.

Many complex systems derived from nature and society consist of multiple types of entities and heterogeneous interactions, which can be effectively modeled as heterogeneous information network (HIN). Structural analysis of heterogeneous networks is of great significance by leveraging the rich semantic information of objects and links in the heterogeneous networks. And, clustering heterogeneous networks aims to group vertices into classes, which sheds light on revealing the structure–function relations of the underlying systems. The current algorithms independently perform the feature extraction and clustering, which are criticized for not fully characterizing the structure of clusters. In this study, we propose a learning model by joint <underline>G</underline>raph <underline>E</underline>mbedding and <underline>N</underline>onnegative <underline>M</underline>atrix <underline>F</underline>actorization (aka GEjNMF ), where feature extraction and clustering are simultaneously learned by exploiting the graph embedding and latent structure of networks. We formulate the objective function of GEjNMF and transform the heterogeneous network clustering problem into a constrained optimization problem, which is effectively solved by l 0 -norm optimization. The advantage of GEjNMF is that features are selected under the guidance of clustering, which improves the performance and saves the running time of algorithms at the same time. The experimental results on three benchmark heterogeneous networks demonstrate that GEjNMF achieves the best performance with the least running time compared with the best state-of-the-art methods. Furthermore, the proposed algorithm is robust across heterogeneous networks from various fields. The proposed model and method provide an effective alternative for heterogeneous network clustering.

Network Representation Learning (NRL), which aims to embed nodes into a latent, low-dimensional vector space while preserving some network properties, facilitates the network analysis tasks. The goal of most NRL methods is to make similar nodes represented similarly in the embedding space. Many methods adopt the skip-gram model to achieve such goal by maximizing the predictive probability among the context nodes for each center node. The context nodes are usually determined based on the concept of \textit{proximity} which is defined based on some explicit network features. However, these proximities may result in a loss of training samples and have limited discriminative power. We propose a general and unified generative adversarial learning framework to address the problems. The proposed framework can handle almost all kinds of networks in a unified way, including homogeneous plain networks, attribute augmented networks and heterogeneous networks. It can improve the performances of the most of the state-of-the-art skip-gram based NRL methods. Moreover, another unified and general NRL method is extended from the framework. It can learn the network representation independently. Extensive experiments on proximity preserving evaluation and two network analysis tasks, i.e., link prediction and node classifications, demonstrate the superiority and versatility of our framework.

Recently, network representation learning has shown its super performance in many network analysis tasks. Traditional network representation learning algorithms mainly mine unilateral network structure information. However, as we move to the age of big data, we can obtain rich auxiliary information from many real-world networks. In this paper, we propose an enhanced network representation learning algorithm by incorporating label and attribute Information. Inspired by natural language model, we propose two novel models: label enhanced attribute information representing model and label enhanced structure information representing model. Then, through parameter sharing strategy and jointly training based on a unified optimization objective function, we can obtain representations of nodes in network preserving network structure, attribute information and label information simultaneously. Experimental results demonstrate that representation vectors obtained by our model outperform state-of-art network representation learning methods on two real-world networks.

BackgroundTraditional drug research and development is high cost, time-consuming and risky. Computationally identifying new indications for existing drugs, referred as drug repositioning, greatly reduces the cost and attracts ever-increasing research interests. Many network-based methods have been proposed for drug repositioning and most of them apply random walk on a heterogeneous network consisted with disease and drug nodes. However, these methods generally adopt the same walk-length for all nodes, and ignore the different contributions of different nodes.ResultsIn this study, we propose a drug repositioning approach based on individual bi-random walks (DR-IBRW) on the heterogeneous network. DR-IBRW firstly quantifies the individual work-length of random walks for each node based on the network topology and knowledge that similar drugs tend to be associated with similar diseases. To account for the inner structural difference of the heterogeneous network, it performs bi-random walks with the quantified walk-lengths, and thus to identify new indications for approved drugs. Empirical study on public datasets shows that DR-IBRW achieves a much better drug repositioning performance than other related competitive methods.ConclusionsUsing individual random walk-lengths for different nodes of heterogeneous network indeed boosts the repositioning performance. DR-IBRW can be easily generalized to prioritize links between nodes of a network.

Content representation is a fundamental task in information retrieval. Representation learning is aimed at capturing features of an information object in a low-dimensional space. Most research on representation learning for heterogeneous information networks (HINs) focuses on static HINs. In practice, however, networks are dynamic and subject to constant change. In this article, we propose a novel and scalable representation learning model, M-DHIN , to explore the evolution of a dynamic HIN. We regard a dynamic HIN as a series of snapshots with different time stamps. We first use a static embedding method to learn the initial embeddings of a dynamic HIN at the first time stamp. We describe the features of the initial HIN via metagraphs, which retains more structural and semantic information than traditional path-oriented static models. We also adopt a complex embedding scheme to better distinguish between symmetric and asymmetric metagraphs. Unlike traditional models that process an entire network at each time stamp, we build a so-called change dataset that only includes nodes involved in a triadic closure or opening process, as well as newly added or deleted nodes. Then, we utilize the above metagraph-based mechanism to train on the change dataset. As a result of this setup, M-DHIN is scalable to large dynamic HINs since it only needs to model the entire HIN once while only the changed parts need to be processed over time. Existing dynamic embedding models only express the existing snapshots and cannot predict the future network structure. To equip M-DHIN with this ability, we introduce an LSTM-based deep autoencoder model that processes the evolution of the graph via an LSTM encoder and outputs the predicted graph. Finally, we evaluate the proposed model, M-DHIN , on real-life datasets and demonstrate that it significantly and consistently outperforms state-of-the-art models.