Dynamic Heterogeneous Networks Research Articles

Neighbor-Enhanced Representation Learning for Link Prediction in Dynamic Heterogeneous Attributed Networks

Dynamic link prediction aims to predict future connections among unconnected nodes in a network. It can be applied for friend recommendations, link completion, and other tasks. Network representation learning algorithms have demonstrated considerable effectiveness in various prediction tasks. However, most network representation learning algorithms are based on homogeneous networks and static networks for link prediction that do not consider rich semantic and dynamic information. Additionally, existing dynamic network representation learning methods neglect the neighborhood interaction structure of the node. In this work, we design a neighbor-enhanced dynamic heterogeneous attributed network embedding method (NeiDyHNE) for link prediction. In light of the impressive achievements of the heuristic methods, we learn the information of common neighbors and neighbors’ interaction in heterogeneous networks to preserve the neighbors proximity and common neighbors proximity. NeiDyHNE encodes the attributes and neighborhood structure of nodes as well as the evolutionary features of the dynamic network. More specifically, NeiDyHNE consists of the hierarchical structure attention module and the convolutional temporal attention module. The hierarchical structure attention module captures the rich features and semantic structure of nodes. The convolutional temporal attention module captures the evolutionary features of the network over time in dynamic heterogeneous networks. We evaluate our method and various baseline methods on the dynamic link prediction task. Experimental results demonstrate that our method is superior to baseline methods in terms of accuracy.

Impact of climate risk on energy market risk spillover: Evidence from dynamic heterogeneous network analysis

Using meteorological monitoring data from eight climate disasters across the globe, the Climate Policy Uncertainty (CPU) Index, and the financial data of eight energy markets between 2010 and 2020, this study employs the fixed base extreme difference entropy method to construct a Climate Risk Index (CRI) and investigates the impact of climate risk on the risk spillover among energy markets based on dynamic heterogeneous network analysis. The results confirm that the CRI fluctuated periodically and exhibited an upward trend during the sample period. In terms of risk spillover, the oil, geothermal, and fuel cell markets act as risk receivers, whereas the gas, wind, and bioenergy markets functions as risk emitters. Climate risk significantly increases the network complexity between energy markets and the risk spillover of gas, solar, water, and wind markets but decreases the risk spillover of oil, bioenergy, fuel cells, and geothermal markets. Additionally, the fossil fuel market is more sensitive to climate risk than is the renewable energy market.

Multi-objective task offloading for highly dynamic heterogeneous Vehicular Edge Computing: An efficient reinforcement learning approach

Vehicular Edge Computing (VEC) provides a flexible distributed computing paradigm for offloading computations to the vehicular network, which can effectively solve the problem of limited vehicle computing resources and meet the on-vehicle computing requests of users. However, the conflict of interest between vehicle users and service providers leads to the need to consider a variety of conflict optimization goals for computing offloading, and the dynamic nature of vehicle networks, such as vehicle mobility and time-varying network conditions, make the offloading effectiveness of vehicle computing requests and the adaptability to complex VEC scenarios challenging. To address these challenges, this paper proposes a multi-objective optimization model suitable for computational offloading of dynamic heterogeneous VEC networks. By formulating the dynamic multi-objective computational offloading problem as a multi-objective Markov Decision Process (MOMDP), this paper designs a novel multi-objective reinforcement learning algorithm EMOTO, which aims to minimize the average task execution delay and average vehicle energy consumption, and maximize the revenue of service providers. In this paper, a preference priority sampling module is proposed, and a model-augmented environment estimator is introduced to learn the environmental model for multi-objective optimization, so as to solve the problem that the agent is difficult to learn steadily caused by the highly dynamic change of VEC environment, thus to effectively realize the joint optimization of multiple objectives and improve the decision-making accuracy and efficiency of the algorithm. Experiments show that EMOTO has superior performance on multiple optimization objectives compared with advanced multi-objective reinforcement learning algorithms. In addition, the algorithm shows robustness when applied to different environmental settings and better adapting to highly dynamic environments, and balancing the conflict of interest between vehicle users and service providers.

HDM-GNN: A Heterogeneous Dynamic Multi-view Graph Neural Network for Crime Prediction

Smart cities have drawn a lot of interest in recent years, which employ Internet of Things (IoT)-enabled sensors to gather data from various sources and help enhance the quality of residents’ life in multiple areas, e.g. public safety. Accurate crime prediction is significant for public safety promotion. However, the complicated spatial-temporal dependencies make the task challenging, due to two aspects: 1) spatial dependency of crime includes correlations with spatially adjacent regions and underlying correlations with distant regions, e.g. mobility connectivity and functional similarity; 2) there are near-repeat and long-range temporal correlations between crime occurrences across time. Most existing studies fall short in tackling with multi-view correlations, since they usually treat them equally without consideration of different weights for these correlations. In this paper, we propose a novel model for region-level crime prediction named as Heterogeneous Dynamic Multi-view Graph Neural Network (HDM-GNN). The model can represent the dynamic spatial-temporal dependencies of crime with heterogeneous urban data, and fuse various types of region-wise correlations from multiple views. Global spatial dependencies and long-range temporal dependencies can be derived by integrating the multiple GAT modules and Gated CNN modules. Extensive experiments are conducted to evaluate the effectiveness of our method using several real-world datasets. Results demonstrate that our method outperforms state-of-the-art baselines. All the code are available at https://github.com/ZJUDataIntelligence/HDM-GNN.

Multi-Agent Collaborative Caching Strategies in Dynamic Heterogeneous D2D Networks

Multi-Agent Collaborative Caching Strategies in Dynamic Heterogeneous D2D Networks

Quasi-synchronization of heterogeneous neural networks with hybrid time delays via sampled-data saturating impulsive control

This paper focuses on the quasi-synchronization matter of directed coupled heterogeneous neural networks with actuator saturation and hybrid time-varying delays under the sampled-data impulsive control. By utilizing the extended impulsive comparison principle and a dead-zone function representation of saturation nonlinearity function, multiple sufficient criteria are established for attaining the quasi-synchronization of heterogeneous dynamic neural networks. Meanwhile, the maximum estimating domain of attraction is acquired by solving an optimization problem which is confined by the linear matrix inequalities converted from the bilinear matrix inequalities. In addition, through utilizing the extended formula for the variation of parameters with hybrid delays, precise exponential convergence rate and theoretical error bound are calculated. Ultimately, the theoretical results are illustrated by means of a numerical simulation.

Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration

Edge intelligence has emerged as a promising paradigm to accelerate DNN inference by model partitioning, which is particularly useful for intelligent scenarios that demand high accuracy and low latency. However, the dynamic nature of the edge environment and the diversity of end devices pose a significant challenge for DNN model partitioning strategies. Meanwhile, limited resources of the edge server make it difficult to manage resource allocation efficiently among multiple devices. In addition, most of the existing studies disregard the different service requirements of the DNN inference tasks, such as its high accuracy-sensitive or high latency-sensitive. To address these challenges, we propose a Multi-Compression Scale DNN Inference Acceleration (MCIA) based on cloud-edge-end collaboration. We model this problem as a mixed-integer multi-dimensional optimization problem, jointly optimizing the DNN model version choice, the partitioning choice, and the allocation of computational and bandwidth resources to maximize the tradeoff between inference accuracy and latency depending on the property of the tasks. Initially, we train multiple versions of DNN inference models with different compression scales in the cloud, and deploy them to end devices and edge server. Next, a deep reinforcement learning-based algorithm is developed for joint decision making of adaptive collaborative inference and resource allocation based on the current multi-compression scale models and the task property. Experimental results show that MCIA can adapt to heterogeneous devices and dynamic networks, and has superior performance compared with other methods.

Exploring Models and Methods of Epidemic Spread in Heterogeneous Dynamic Networks: A Comparative Analysis

Exploring Models and Methods of Epidemic Spread in Heterogeneous Dynamic Networks: A Comparative Analysis

Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing

Heterogeneous Dynamic Graph Convolutional Networks for Enhanced Spatiotemporal Flood Forecasting by Remote Sensing

Multiple Access via Curriculum Multi-Task HAPPO Based in Dynamic Heterogeneous Wireless Network

Multiple Access via Curriculum Multi-Task HAPPO Based in Dynamic Heterogeneous Wireless Network

A product requirement influence analysis method based on multilayer dynamic heterogeneous networks

With the promotion of emerging technologies in the era of big data, there has been a diversification in user participation in product requirement development. This has resulted in many complex, diverse, and rapidly iterated user requirements, greatly reducing the applicability of traditional requirement development methods. In this paper, to address the complex and ever-changing relationships among users, requirements, products, and requirement development teams in the product development process, a multilayer dynamic heterogeneous network node influence analysis method is constructed for product requirement development. This method establishes a product requirement development framework based on a multilayer dynamic heterogeneous network consisting of a user layer, requirement layer, component layer, and expert layer in terms of three dimensions: requirement development, requirement evaluation, and time. Based on this framework, indicators such as comprehensive node significance, layer significance, and node influence are designed. To address the issues encountered in small sample data testing, three measurement models are further designed in this paper, effectively improving the sampling efficiency of the multilayer dynamic heterogeneous network. Additionally, calculation models for the comprehensive node influence and comprehensive node influence variation rate are improved and constructed, and corresponding algorithms are designed. This method is applied in an experimental study of product requirement development for new energy vehicles, providing high-quality recommendations for new energy vehicle requirement developers, including functional requirements and product components that need close and timely attention. Moreover, accuracy tests show that the proposed algorithm achieves an average accuracy rate of 0.8611, which is significantly higher than those of other network node centrality measurement methods. This demonstrates the advanced nature and applicability of the proposed method in the field of product requirement development, providing a new way for requirement developers to improve work efficiency.

Multi-hop community question answering based on multi-aspect heterogeneous graph

Community question answering aims to connect queries and answers based on users' community behaviors, find the most relevant solutions for newly raised questions, and improve community activity. Existing research mainly focuses on the single-hop method, which relies on a particular feature for simple question answering. However, multi-hop question answering, which depends on multi-step reasoning to solve complex questions, still faces the destitute adaptability caused by various entity features and complex entity correlations. In this work, we put forward a Multi-Hop Community Question-Answering method called MHCQA, that combines the multi-aspect features of community entities, constrains the answer retrieval process from different perspectives and improves the adaptability of multi-hop answer retrieval. Firstly, we utilize phrases for representing the semantic features of question-answering and fuse them with entity constitution properties through heterogeneous graphs to effectively indicate the diverse relationships among entities in communities. At the same time, we bring a dynamic heterogeneous network construction strategy to improve the efficiency of feature representation. Secondly, we enhance heterogeneous graph attention networks for efficiently computing local entity similarities to find relevant answers to questions based on partial graphs. Finally, we propose a multi-constraint multi-hop community question-answering method, which optimizes answer retrieval from three aspects: the hop count, the number of answers, and the relevance of responses, to improve the scene adaptability of multi-hop answer retrieving. Abundant experiments on realistic corpus (Quora, Math, Super User, and Stack Overflow) illustrate that MHCQA improves the multi-hop question answering error rate by about 2 % and is about 11 % ahead of the baselines in terms of operating efficiency. Given our present literature survey, MHCQA is a promising research idea for automatic answering services in online question-answering communities.

Deep Temporal Graph Infomax for Imbalanced Insider Threat Detection

ABSTRACT Insider threats pose a significant concern for critical information infrastructures. Graph neural networks are widely used for detection due to their ability to model complex relationships among network entities. However, deep learning algorithms struggle with learning from business system data as anomalies are extremely rare. To tackle this challenge, we propose deep temporal graph infomax (DTGI), a new method for detecting insider threats in real-world scenarios with highly imbalanced data. DTGI utilizes an extended continuous-time dynamic heterogeneous graph network and a behavior context constraint anomaly sample generator. This generator incorporates attack behavior context constraints to augment attack samples and enhance the performance of the supervised model. Extensive experiments conducted on the CERT dataset, consisting of over one million records, demonstrate that DTGI surpasses state-of-the-art methods in terms of detection performance.

The Event-Triggered Impulsive Controls for Quasisynchronization of the Leader-Following Heterogeneous Dynamical Networks.

The time-triggered impulsive controls were widely used to study the collective behavior of homogeneous dynamical networks due to their low control cost, which was a bit conservative in the occupation of communication channels. This article addresses designing the event-triggered impulsive controls for the quasisynchronization, namely, a weak cooperative behavior with the synchronization error no more than a positive constant in the leader-following heterogeneous dynamical network, which thus can reduce the occupation of resources significantly. The centralized and distributed impulsive controls are designed to lead the followers to synchronize approximately to the leader within a nonzero bound, where the impulsive instants are triggered, respectively, by the global or local state-dependent conditions. Numerical results are put forward to verify the effectiveness of the proposed methods.

A Study on Enhancing Channel Estimation in Vehicular Communications: Metamaterial-Enhanced Microstrip Antennas

Vehicular communication systems play a pivotal role in modern transportation, offering solutions for traffic management, road safety, and infotainment services. Effective optimization of channel estimation in these systems is imperative to overcome inherent challenges. This paper has explored the issues that hinder reliable and efficient channel estimation in vehicular communications. High mobility and dynamic environments, multipath fading, heterogeneous networks, scalability, and security and privacy concerns were identified as key challenges. Addressing these challenges is crucial for ensuring the robustness and effectiveness of vehicular communication systems. By advancing channel estimation techniques, we can enhance data throughput, reduce latency, and improve overall network performance, ultimately contributing to safer and more efficient transportation systems.

Application of app intelligent voice software based on dynamic heterogeneous network in TPACK oral English teaching

Application of app intelligent voice software based on dynamic heterogeneous network in TPACK oral English teaching

Intralayer Synchronization in Heterogeneous Multiplex Dynamical Networks Based on Spectral Graph Theory

Intralayer Synchronization in Heterogeneous Multiplex Dynamical Networks Based on Spectral Graph Theory

The Logic of Homophily Dynamics in Heterogeneous Networks: Axiomatization, Model Checking and Validity Checking

Social networks have received considerable attention from the modal logic community. In this article, we study and characterize one of the most important principles in the field of social networks. Homophily, which means similarity breeds association, reveals the nature of social organization. In order to be able to express similarity and association together, we generalize the basic network and then define the heterogeneous network. The heterogeneous network is also defined to provide a good foundation for the use of logical approaches. The Logic of Homophily LHG,M that we propose in this article is based on Computation Tree Logic and Formal Concept Analysis. LHG,M describes the homophily dynamics of the heterogeneous networks at a specified similarity coefficient. Furthermore, we not only axiomatize the LHG,M and prove that the axiom system LHG,Mn is sound and complete, but we also prove that the model checking and the validity checking for LHG,M are both PSPACE-complete.

Network alignment and link prediction using event-based embedding in aligned heterogeneous dynamic social networks

Network alignment and link prediction using event-based embedding in aligned heterogeneous dynamic social networks

Tackling higher-order relations and heterogeneity: Dynamic heterogeneous hypergraph network for spatiotemporal activity prediction

Spatiotemporal activity prediction aims to predict user activities at a particular time and location, which is applicable in city planning, activity recommendations, and other domains. The fundamental endeavor in spatiotemporal activity prediction is to model the intricate interaction patterns among users, locations, time, and activities, which is characterized by higher-order relations and heterogeneity. Recently, graph-based methods have gained popularity due to the advancements in graph neural networks. However, these methods encounter two significant challenges. Firstly, higher-order relations and heterogeneity are not adequately modeled. Secondly, the majority of established methods are designed around the static graph structures that rely solely on co-occurrence relations, which can be imprecise. To overcome these challenges, we propose DyH2N, a dynamic heterogeneous hypergraph network for spatiotemporal activity prediction. Specifically, to enhance the capacity for modeling higher-order relations, hypergraphs are employed in lieu of graphs. Then we propose a set representation learning-inspired heterogeneous hyperedge learning module, which models higher-order relations and heterogeneity in spatiotemporal activity prediction using a non-decomposable manner. To improve the encoding of heterogeneous spatiotemporal activity hyperedges, a knowledge representation-regularized loss is introduced. Moreover, we present a hypergraph structure learning module to update the hypergraph structures dynamically. Our proposed DyH2N model has been extensively tested on four real-world datasets, proving to outperform previous state-of-the-art methods by 5.98% to 27.13%. The effectiveness of all framework components is demonstrated through ablation experiments.