Different Types Of Nodes Research Articles

Multi-level discriminator based contrastive learning for multiplex networks

Graph embedding is a technique for obtaining low-dimensional representations of nodes across diverse networks, which may then be used for various downstream tasks and applications. When it applies to heterogeneous networks, it is hard to handle heterogeneous networks because they usually contain different types of nodes and edges with more semantic and structural information. Recently, contrastive learning has developed as the preferred strategy for dealing with unsupervised heterogeneous graph embedding to reduce the cost of human label annotation. However, most multi-view contrastive learning approaches calculate the model’s loss only based on the mutual dependence between the node representation and graph representation. These approaches ignore that both node attributes and node clustering contain discriminative content. To solve this issue, we propose a model called Multi-Level Discriminator-based Contrastive Learning for Multiplex Networks (MLDCL). This model adopts a multi-level multi-discriminator-based approach that can simultaneously learn the global-level structural information, node-level attribute information, and local-level clustering information. Moreover, an augmentation strategy in the contrast learning process from the spectral domain is proposed to improve the representation and discriminative ability of MLDCL. Numerous tests with node clustering and classification tasks on widely used datasets demonstrate the efficacy of the proposed approach.

Jamming avoidance trajectory planning and load balancing user association in mmWave UAV-assisted HetECN

Emergency communication network (ECN) can provide fast, efficient and high-capacity communication services for specific areas by using mmWave transmission and unmanned aerial vehicles (UAVs) serving as aerial base stations (ABSs) or relay nodes. Now, in order to satisfy diverse demands, ECN should support different types of nodes, access methods, and traffic distributions, which is referred to as heterogeneous ECN (HetECN). Therefore, inappropriate trajectory planning and unbalanced traffic loading can lead to UAV flight collisions and network congestion. In this article, we jointly optimize UAV jamming avoidance trajectory and user association strategy aimed to load balancing, to maximize the utilization of HetECN. Specifically, an improved artificial potential field (APF) method along with mmWave beam forming technology is used to obtain the jamming avoidance trajectory of UAVs, and the optimal deployment location of UAVs are determined based on the distribution of ground users (GUs). Subsequently, the matching game and alliance game are comprehensively used to determine the load balancing based GU-UAV associated strategy under various GU demands, thereby ensuring traffic load balancing and resource optimization allocation. In addition, altitude fine-tuning have been made to further power consumption, thereby improving overall network efficiency. Simulation results demonstrate that the proposed method can achieve the expected performance in network utilities such as coverage rate, network capacity, load balancing effect of mmWave UAV-assisted HetECNs.

Dual-neighbourhood information aggregation and feature fusion for prediction of miRNA–disease association

Studying the intricate relationship between miRNAs and diseases is crucial to prevent and treat miRNA-related disorders. Existing computational methods often overlook the importance of features of different nodes and the propagation of features among heterogeneous nodes. Many prediction models focus only on the feature coding of miRNA and diseases and ignore the importance of feature aggregation. We propose a prediction method via dual-neighbourhood feature aggregation and feature fusion, which uses multiple sources of information, aggregates information on homogeneous and heterogeneous nodes and fuses learned features to predict multiple representations of disease nodes. We constructed similarity networks of multiple homogeneous nodes based on different similarity computation methods respectively, and fused the attention mechanism by using graph convolutional networks to obtain information of different levels of importance. To alleviate the problem of sparse connectivity in the dataset, we built a two-neighbourhood heterogeneous graph neural network model to integrate the homogeneous similarity network into a miRNA-disease heterogeneous network by using known miRNA–disease association information. We used the neighbourhood information associated with the nodes in the network to perform feature aggregation. In addition, we used a feature fusion module to learn the importance of different types of nodes to predict miRNA–disease associations. Our experimental results on the Human microRNA Disease Database (HMDD v3.2) show that the model demonstrates superior performance. This work demonstrates the capability of our model to identify potential miRNAs associated with diseases through a case study of two common cancers.

DyHDGE: Dynamic heterogeneous transaction graph embedding for safety-centric fraud detection in financial scenarios

Dynamic graph fraud detection aims to distinguish fraudulent entities that deviate significantly from most benign entities within an ever-changing graph network. However, when dealing with different financial fraud scenarios, existing methods face challenges, resulting in difficulty in effectively ensuring financial security. In fraud scenarios, transaction data are generated in real time, in which a strong temporal relationship between multiple fraudulent transactions is observed. Traditional dynamic graph models struggle to effectively balance the temporal features of nodes and spatial structural features, failing to handle different types of nodes in the graph network. In this study, to extract the temporal and structural information, we proposed a dynamic heterogeneous transaction graph embedding (DyHDGE) network based on a dynamic heterogeneous transaction graph, considering both temporal and structural information while incorporating heterogeneous data. To separately extract temporal relationships between transactions and spatial structural relationships between nodes, we used a heterogeneous temporal graph representation learning module and a temporal graph structure information extraction module. Additionally, we designed two loss functions to optimize node feature representations. Extensive experiments demonstrated that the proposed DyHDGE significantly outperformed previous state-of-the-art methods on two simulated datasets of financial fraud scenarios. This capability contributes to enhancing security in financial consumption scenarios.

Unsupervised Heterogeneous Graph Neural Networks for One-Class Tasks: Exploring Early Fusion Operators

Heterogeneous graphs are an essential structure that models real-world data through different types of nodes and relationships between them, including multimodality, which comprises different types of data such as text, image, and audio. Graph Neural Networks (GNNs) are a prominent graph representation learning method that takes advantage of the graph structure and its attributes that, when applied to the multimodal heterogeneous graph, learn a unique semantic space for the different modalities. Consequently, it allows multimodal fusion through simple operators such as sum, average, or multiplication, generating unified representations considering the supplementary and complementarity relationships between the modalities. In multimodal heterogeneous graphs, the labeling process tends to be even more costly due to the multiple modalities analyzed, in addition to the imbalance of classes inherent to some applications. In order to overcome these problems in applications that comprise a class of interest, One-Class Learning (OCL) is used. Given the lack of studies on multimodal early fusion in heterogeneous graphs for OCL tasks, we proposed a method based on unsupervised GNN for heterogeneous graphs and evaluated different early fusion operators. In this paper, we extend another work by evaluating the behavior of the main GNN convolutions in the method. We highlight that using operators such as average, addition, and subtraction were the best early fusion operators. In addition, GNN layers that do not use an attention mechanism performed better. In this way, we argue for heterogeneous graph neural networks in multimodal using early fusion simple operators instead of well-often-used concatenation and less complex convolutions.

A heterogeneous graph neural network with automatic discovery of effective metapaths for drug–target interaction prediction

Predicting potential Drug–Target Interactions (DTIs) is a critical step in drug discovery. In recent years, graph machine learning methods based on heterogeneous networks have garnered significant attention and have demonstrated advantages in predicting potential DTIs. However, existing methods require the specification of metapaths for different types of nodes to learn node features, which fails to fully and effectively mine the high-order relationships between nodes. Moreover, most methods do not generate meaningful embeddings for nodes in the network, relying solely on the network’s topological structure to learn feature representations of drugs and targets. To address these limitations, we propose a novel DTI prediction framework based on heterogeneous networks, named ADEM, which can Automatically Discover Effective Metapaths for any type of node. In addition, this framework employs similarity constraints as prior knowledge to generate meaningful embeddings for nodes in the network. ADEM outperforms classical and state-of-the-art models on three benchmark DTI datasets. Experimental analysis validates the effectiveness and rationality of the ADEM framework and its individual modules. Furthermore, the metapaths discovered by ADEM can enhance the performance of existing models in DTI prediction tasks.

Influence maximization for heterogeneous networks based on self-supervised clustered heterogeneous graph transformer

Influence maximization (IM) has drawn significant attention in recent years. Most existing IM methods primarily focus on homogeneous networks, and do not take into account the heterogeneity and the attributes of different types of nodes in heterogeneous networks. However, heterogeneous networks are ubiquitous in real world, encompassing rich semantics and complex structural information. Additionally, the clustering characteristics inherent in a network have a critical and substantial impact on the process of information diffusion, which is often overlooked in IM models designed for heterogeneous networks. To address the challenges posed by the heterogeneity and clustering structure in heterogeneous networks, we propose a novel deep learning framework based on a self-supervised clustered heterogeneous graph transformer for IM in heterogeneous networks, which we have named SCHGT-IM. SCHGT-IM aggregates the heterogeneity and clustering information in heterogeneous networks and incorporates a clustered cascade (CC) model as an information diffusion model to enhance the realism of simulations. We evaluate the performance of SCHGT-IM in comparison with that of state-of-the-art IM models using three academic heterogeneous networks extracted from the DBLP dataset. The experimental results on influence spread demonstrate that SCHGT-IM is superior to fourteen state-of-the-art algorithms and is highly effective in selecting influential seed nodes of different types from heterogeneous networks.

The impact of patentees assessment based on the heterogeneous patent innovation network

As a vital factor in technological innovation, patentee plays a significant role in the process of scientific and technological innovation, researching patentee has attracted the attention of experts and scholars. Previously, scholars have mainly quantified patent indicators or constructed homogeneous information networks to analyze patentees, but these methods cannot objectively measure the impact of patentees. Therefore, this study proposes a novel approach to assessing patentee impact based on a heterogeneous information network. The proposed method distinguishes the weight of different types of nodes using a weighted mechanism and extracts three types of fine-grained characteristics of network nodes. This approach results in the construction of a heterogeneous patent innovation network and the development of a new patentee impact assessment algorithm called CWAPN. Using Chinese green patents in the field of energy conservation and environmental protection as an example, experimental results show that the CWAPN algorithm can effectively assess the impact of patentees. Thereby identifying patentees who have made outstanding contributions to sustainable development in China.

Railway network delay evolution: A heterogeneous graph neural network approach

Accurate delay evolution prediction plays a pivotal role in train rescheduling decision-making for the railway network. Existing studies on delay prediction predominantly centered around predicting delays for each train in the subsequent stations (i.e., following a train-oriented perspective). Furthermore, train operations in the railway network involve different types of entities (stations, trains, etc.), making the current graph/network models with homogenous nodes (i.e., the same kind of nodes) incapable of effectively capturing the interactions between the entities. This paper develops a network-oriented model to investigate the train delay evolution on railway networks, by predicting the delays of running trains in the network after a given time interval. The proposed model combines the GraphSAGE graph neural network (GNN) and the heterogeneous graph neural network (HetGNN) architecture, thus called SAGE-Het, enabling it to capture interactions between heterogeneous nodes (i.e., different types of nodes) based on different edges (e.g., edges between trains, trains, and stations). Additionally, SAGE-Het allows for flexible inputs in contrast to conventional machine learning techniques, whose inputs must meet the consistent dimension requirement (e.g., in the form of rectangular or grid-like arrays). The performance and robustness of the suggested SAGE-Het model are assessed in experiments on the data from two sub-networks of the China railway network. The experimental results demonstrate that SAGE-Het outperforms the existing delay prediction methods and some advanced HetGNNs used for prediction tasks in other domains; SAGE-Het demonstrates excellent scalability, capable of handling various types of nodes; the predictive performances of SAGE-Het under different prediction time horizons (10/20/30 min ahead) all exhibit better performance over other baselines; the accuracies are over 90 % under the permissible 3-minute errors for the three prediction time horizons. Specifically, the impact of train interactions on delay evolution is investigated based on the flexible input characteristic of the proposed model. The results illustrate that train interactions become subtle with the increase of train headways. This finding directly contributes to decision-making in situations where conflict resolution or train-canceling actions are needed.

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.

Performance evaluation of handover triggering condition estimation using mobility models in heterogeneous mobile networks

AbstractHeterogeneous networks (HetNets) refer to the communication network, consisting of different types of nodes connected through communication networks deploying diverse radio access technologies like LTE, Wi‐Fi, Zigbee, and Z‐wave, and using different communication protocols and operating frequencies. Vertical handover, is the process of switching a mobile device from one network type to another, such as from a cellular network to a Wi‐Fi network, and is critical for ensuring a seamless user experience and optimal network performance, within the handover process handover triggering estimation is one of the crucial step affecting the overall performance. A mathematical analysis is presented for the handover triggering estimation. The performance evaluation shows significant improvement in the probability of successful handover using the proposed handover triggering condition based on speed, distance, and different mobility models. The handover triggering condition is optimised based on the speed of the mobile node, handover completion time, and the coverage range of the current and the target networks of the HetNet node, with due consideration of the mobility model.

Graph neural network recommendation algorithm based on improved dual tower model

In this era of information explosion, recommendation systems play a key role in helping users to uncover content of interest among massive amounts of information. Pursuing a breadth of recall while maintaining accuracy is a core challenge for current recommendation systems. In this paper, we propose a new recommendation algorithm model, the interactive higher-order dual tower (IHDT), which improves current models by adding interactivity and higher-order feature learning between the dual tower neural networks. A heterogeneous graph is constructed containing different types of nodes, such as users, items, and attributes, extracting richer feature representations through meta-paths. To achieve feature interaction, an interactive learning mechanism is introduced to inject relevant features between the user and project towers. Additionally, this method utilizes graph convolutional networks for higher-order feature learning, pooling the node embeddings of the twin towers to obtain enhanced end-user and item representations. IHDT was evaluated on the MovieLens dataset and outperformed multiple baseline methods. Ablation experiments verified the contribution of interactive learning and high-order GCN components.

Random walk with restart on multilayer networks: from node prioritisation to supervised link prediction and beyond

BackgroundBiological networks have proven invaluable ability for representing biological knowledge. Multilayer networks, which gather different types of nodes and edges in multiplex, heterogeneous and bipartite networks, provide a natural way to integrate diverse and multi-scale data sources into a common framework. Recently, we developed MultiXrank, a Random Walk with Restart algorithm able to explore such multilayer networks. MultiXrank outputs scores reflecting the proximity between an initial set of seed node(s) and all the other nodes in the multilayer network. We illustrate here the versatility of bioinformatics tasks that can be performed using MultiXrank.ResultsWe first show that MultiXrank can be used to prioritise genes and drugs of interest by exploring multilayer networks containing interactions between genes, drugs, and diseases. In a second study, we illustrate how MultiXrank scores can also be used in a supervised strategy to train a binary classifier to predict gene-disease associations. The classifier performance are validated using outdated and novel gene-disease association for training and evaluation, respectively. Finally, we show that MultiXrank scores can be used to compute diffusion profiles and use them as disease signatures. We computed the diffusion profiles of more than 100 immune diseases using a multilayer network that includes cell-type specific genomic information. The clustering of the immune disease diffusion profiles reveals shared shared phenotypic characteristics.ConclusionOverall, we illustrate here diverse applications of MultiXrank to showcase its versatility. We expect that this can lead to further and broader bioinformatics applications.

Generalized latent space model for one-mode networks with awareness of two-mode networks

Latent space models have been widely studied for one-mode networks, in which the same type of nodes connect with each other. In many applications, one-mode networks are often observed along with two-mode networks, which reflect connections between different types of nodes and provide important information for understanding the one-mode network structure. However, the classical one-mode latent space models have several limitations in incorporating two-mode networks. To address this gap, a generalized latent space model is proposed to capture common structures and heterogeneous connecting patterns across one-mode and two-mode networks. Specifically, each node is embedded with a latent vector and network-specific degree parameters that determine the connection probabilities between nodes. A projected gradient descent algorithm is developed to estimate the latent vectors and degree parameters. Moreover, the theoretical properties of the estimators are established and it has been proven that the estimation accuracy of the shared latent vectors can be improved through incorporating two-mode networks. Finally, simulation studies and applications on two real-world datasets demonstrate the usefulness of the proposed model.

Vulnerability Analysis of China‐Europe Railway Express Network Based on Improved Nonlinear Load‐Capacity Model

The China‐Europe Railway Express (C‐ER Express) provides a transcontinental rail container service between China and Europe. As most C‐ER Expresses are affected by frequent natural disasters and public health incidents, it faces the increasing risk of network vulnerability. When previous studies investigated the evolution of network vulnerability through local information, they often overlook the complexity of the network’s multidimensional characteristics. The nonlinear load‐capacity (NLC) model proposed in this paper integrates local and global information of the network. This approach enables a detailed investigation into how condition thresholds and different types of nodes influence network vulnerability. Firstly, a feature matrix is constructed for C‐ER Express based on the topological measures, freight information, and external environment scores. Then, the autoencoder is used to extract the low‐dimensional dense information, and the DBSCAN is used to classify C‐ER Express into distinct clusters. Secondly, The NLC model integrates feature coefficient to describe the initial capacity of nodes. Subsequently, the failure load is redistributed proportionally to neighboring nodes and remaining normal nodes based on time‐varying load and initial capacity of nodes. Finally, the improved NLC model is applied to the C‐ER Express under different simulation scenarios. Simulation results show that a reasonable condition threshold can mitigate the impact of small‐scale node failures on the network. The DBSCAN attack strategy can effectively identify the node types and prevent the network from chain reactions brought by different types of node failures. This research study is expected to provide some reference value for relevant research about vulnerability analysis of the C‐ER Express network.

The application of heterogeneous graph neural network and deep reinforcement learning in hybrid flow shop scheduling problem

The hybrid flow shop scheduling problem (HFSP) is a fundamental optimization problem in the process industries. HFSP needs to consider both job selection and machine allocation. The existing HFSP solution methods represented by deep reinforcement learning (DRL) are challenging to extract complex state features and lack certain adaptability in dealing with large-scale HFSP. To solve HFSP with a large scale and relatively strong flexibility, we propose an end-to-end DRL architecture based on the heterogeneous graph neural network to learn an optimal scheduling policy. First of all, by adding a set of machine nodes, the disjunctive graph of the traditional flexible scheduling problem is extended and transformed into a heterogeneous graph, which intuitively represents the allocation relationship between operations and machines, and it is regarded as the scheduling state at different times; secondly, a new HFSP heterogeneous graph neural network (HGNN) algorithm is established to embed potential relationships between different types of nodes and edges, and an embedding of the entire graph is generated; finally, we use the graph-level representation vectors of heterogeneous graphs as input to the proximal policy optimization (PPO) algorithm for learning the optimal scheduling policy. The experimental results show that compared with several well-known heuristic algorithms, the scheduling policy obtained by the architecture through learning can have good generalization performance in simple and complex problems, respectively, and has a relatively high solution efficiency.

Mapping time series into signed networks via horizontal visibility graph

Time series could be mapped into complex networks through the visibility or horizontal visibility algorithms, and the properties of the constructed network reflect the nonlinear dynamics of the time series. When horizontal visibility algorithm is directly applied to climate anomaly time series, in which both local maximum and local minimum are equally important, local minimum might be “overlooked”. In this paper, we propose a new method that maps climate anomaly time series into signed networks. Positive and negative data values of climate anomaly time series are classified into two types and mapped as nodes of signed networks. Links connecting nodes of the same type are assigned positive signs, while links connecting neighboring nodes of different types are assigned negative signs. This method is also applicable to time series those are assumed to be “stationary” or with no significant trends. Four kinds of degree as well as the degree distributions of the signed networks have been defined. Specifically, the degree and degree distribution could be partly derived analytically for periodic and uncorrelated random time series. The theoretical predictions for periodic and uncorrelated random time series have also been verified by extensive numerical simulations. Based on the entropy of the distribution of net degree, we propose a new complexity measure for chaotic time series. Compared to some previous complexity measures, the new complexity measure is an objective measure without transforming continuous values into discrete probability distributions but still has higher accuracy and sensitivity. Moreover, correlation information of stochastic time series can also be extracted via a topological parameter, the mean of ratio degree, of the signed networks. The extraction of serial correlation has been illustrated through numerical simulations and verified through an empirical climate time series.

Link prediction in bipartite networks via effective integration of explicit and implicit relations

Link prediction in bipartite networks aims to identify or predict possible links between nodes of different types based on known network information. However, most existing studies predominantly focus on monopartite networks, neglecting the intrinsic properties unique to bipartite networks, such as the intricate high-order relationships between nodes. Both explicit relations (representing low-order information) and implicit relations (representing high-order information) play essential roles in predicting the evolution of bipartite networks, and they are indispensable and mutually reinforce each other. To fully leverage their potential in addressing the link prediction problem, we propose a novel framework from the perspective of network representation. This framework not only effectively integrates explicit relations and implicit relations, but also preserves the local and global structure of bipartite networks. Specifically, the probability of a link between two nodes of different types is determined by the linear sum of the contribution values of the mutually connected nodes in their respective common neighbors. Implicit relations are then used to preserve the local structure during the network representation. Furthermore, we implement optimization using a relaxed majorization-minimization algorithm, offering the advantage of uncovering high-quality local minima. Our proposed framework has undergone extensive testing on eight real-world datasets, and the results unequivocally demonstrate its significant superiority over state-of-the-art methods.

HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding.

Encoding a driving scene into vector representations has been an essential task for autonomous driving that can benefit downstream tasks e.g., trajectory prediction. The driving scene often involves heterogeneous elements such as the different types of objects (agents, lanes, traffic signs) and the semantic relations between objects are rich and diverse. Meanwhile, there also exist relativity across elements, which means that the spatial relation is a relative concept and need be encoded in a ego-centric manner instead of in a global coordinate system. Based on these observations, we propose Heterogeneous Driving Graph Transformer (HDGT), a backbone modelling the driving scene as a heterogeneous graph with different types of nodes and edges. For heterogeneous graph construction, we connect different types of nodes according to diverse semantic relations. For spatial relation encoding, the coordinates of the node as well as its in-edges are in the local node-centric coordinate system. For the aggregation module in the graph neural network (GNN), we adopt the transformer structure in a hierarchical way to fit the heterogeneous nature of inputs. Experimental results show that HDGT achieves state-of-the-art performance for the task of trajectory prediction, on INTERACTION Prediction Challenge and Waymo Open Motion Challenge.

Multiple Information-Aware Recurrent Reasoning Network for Joint Dialogue Act Recognition and Sentiment Classification

The task of joint dialogue act recognition (DAR) and sentiment classification (DSC) aims to predict both the act and sentiment labels of each utterance in a dialogue. Existing methods mainly focus on local or global semantic features of the dialogue from a single perspective, disregarding the impact of the other part. Therefore, we propose a multiple information-aware recurrent reasoning network (MIRER). Firstly, the sequence information is smoothly sent to multiple local information layers for fine-grained feature extraction through a BiLSTM-connected hybrid CNN group method. Secondly, to obtain global semantic features that are speaker-, context-, and temporal-sensitive, we design a speaker-aware temporal reasoning heterogeneous graph to characterize interactions between utterances spoken by different speakers, incorporating different types of nodes and meta-relations with node-edge-type-dependent parameters. We also design a dual-task temporal reasoning heterogeneous graph to realize the semantic-level and prediction-level self-interaction and interaction, and we constantly revise and improve the label in the process of dual-task recurrent reasoning. MIRER fully integrates context-level features, fine-grained features, and global semantic features, including speaker, context, and temporal sensitivity, to better simulate conversation scenarios. We validated the method on two public dialogue datasets, Mastodon and DailyDialog, and the experimental results show that MIRER outperforms various existing baseline models.