Network Datasets Research Articles

The development of a routable pavement network dataset to support active travel

ABSTRACT Active travel (AT) networks have only recently become a priority for urban planners in many countries, and networks of spatial data and applications that use them are also lacking. Road networks have historically been used as a proxy for pedestrian networks, yet they are a poor one as human movement is much less constrained than that of motorised vehicles. This study presents a novel approach to producing an attribute-rich network for AT, together with a semi-automated method to produce a width-attributed pavement network from topographic mapping agency data (based on a case study of Ordnance Survey (OS) MasterMap data from the UK). A shortest path network routing application using Dijkstra’s algorithm is presented to demonstrate the possibilities of AT routing incorporating increased attribution. The paper concludes by firstly proposing additional steps to further enhance the attribution of the network and finally by describing the relevant policy implications of this work.

DGTNet：dynamic graph attention transformer network for traffic flow forecasting

Abstract Graph-based traffic flow prediction plays a crucial role in urban traffic management and planning. In this paper, we propose a novel Dynamic Graph Attention Transformer Network (DGTnet), which is designed to address the issue of inadequately integrating of temporal and spatial dimensions in traditional models. DGTnet maintains temporal continuity while revealing the complex dynamic relationships between key nodes in the urban traffic system, capturing the periodic changes in the rhythm of city life. Specifically, this study adopts adaptive signal decomposition technology to decompose traffic data into multiple intrinsic mode functions (IMFs), effectively capturing the dynamic changes in traffic flow. This decomposition method is key to the implementation of DGTnet dynamic graph construction, enabling the analysis of traffic flow at different time scales, thereby providing a new perspective for traffic flow prediction research. In the traffic prediction module, we comprehensively consider node, edge, and graph structural information, adopting a multi-head self-attention mechanism to achieve direct cross-modeling in both temporal and spatial dimensions. Finally, we introduce a position-wise feed forward network layer to integrate different types of data and capture nonlinear relationships. The experimental results, based on the public transportation network data sets METR_LA, PEMS_BAY, PEMS03 and PEMS07, demonstrate that DGTNet exhibits notable enhancements in three evaluation indicators, namely the Mean Absolute Percentage Error (MAPE), the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). The pertinent code has been made available for public access at https://github.com/chenjing0616/DGTNet.

Model Parameter Prediction Method for Accelerating Distributed DNN Training

As the size of deep neural network (DNN) models and datasets increases, distributed training becomes popular to reduce the training time. However, a severe communication bottleneck in distributed training limits its scalability. Many methods aim to solve this communication bottleneck by reducing communication traffic, such as gradient sparsification and quantification. However, these methods either are at the expense of losing model accuracy or introducing lots of computing overhead. We observe that the data distribution between layers of neural network models is similar. Thus, we propose a model parameter prediction method (MP2) to accelerate distributed DNN training under parameter server (PS) framework, where workers push only a subset of model parameters to PS, and residual model parameters are locally predicted by an already-trained deep neural network model on PS. Some key challenges are addressed. First, we build a hierarchical parameters dataset by randomly sampling a subset of model from normal distributed trainings. Second, we build a neural network model with the structure of “convolution + channel attention + Max pooling” for predicting model parameters by using a prediction result-based evaluation method. For VGGNet, ResNet, and AlexNet models on CIFAR10 and CIFAR100 datasets, compared with Baseline, Top-k, deep gradient compression (DGC), and weight nowcaster network (WNN), MP2 can reduce traffic by up to 88.98%; and accelerates the training by up to 47.32% while not losing the model accuracy. MP2 has shown good generalization.

Synergistic Integration of Local and Global Information for Critical Edge Identification

Identifying critical edges in complex networks is a fundamental challenge in the study of complex networks. Traditional approaches tend to rely solely on either global information or local information. However, this dependence on a single information source fails to capture the multi-layered complexity of critical edges, often resulting in incomplete or inaccurate identification. Therefore, it is essential to develop a method that integrates multiple sources of information to enhance critical edge identification and provide a deeper understanding and optimization of the structure and function of complex networks. In this paper, we introduce a Global–Local Hybrid Centrality method which integrates a second-order neighborhood index, a first-order neighborhood index, and an edge betweenness index, thus combining both local and global perspectives. We further employ the edge percolation process to evaluate the significance of edges in maintaining network connectivity. Experimental results on various real-world complex network datasets demonstrate that the proposed method significantly improves the accuracy of critical edge identification, providing theoretical and methodological support for the analysis and optimization of complex networks.

Revealing the closeness of publication ties in scientific cooperation taking into account scientific productivity based on the Time-Weighted PageRank Method with Citation Intensity

The object of this study is the processes related to the assessment of the closeness of publication ties among scientists and taking into account their productivity related to scientific activity. This is necessary to increase the efficiency of management of research projects. To this end, the PR, TWPR, TWPR-CI methods for calculating scientific productivity estimates of scientists were described. In particular, the TWPR-CI method gives preference to those scientists whose works were more intensively published and cited during the last period of time, which is important for the formation of the composition of the executors of scientific research projects. The method for calculating the closeness of publication ties among scientists or average asymmetric tie strength was also described. The verification of dependence between the evaluation of the closeness of publication ties among scientists and their scientific productivity was carried out based on the analysis of the citation network of scientific publications and the network of scientific cooperation. The networks are built on the basis of the open access Citation Network Dataset (ver. 14). The dataset contains information on more than 5 million scientific publications and more than 36 million citations to them. The correlation analysis revealed the presence of a weak inverse relationship between these estimates. However, the weakness of the connection allows us to state that for this case there is no established correlation between the assessment of scientific productivity and the assessment of the closeness of publication ties. That is, the hypothesis that the weak connection between scientists makes it possible to increase the productivity and innovativeness of their publications was not confirmed. The results allow for a systematic approach to the process of evaluation and planning of the results of research projects, as well as the formation of the composition of their executors

Sine Cosine Algorithm Based on Optimal Convolutional Autoencoder for Intrusion Detection and Classification Models

Network security comprises a multifaceted method that aims to protect computer networks from malicious activities, unauthorized access, and data breaches. The security mechanism is Intrusion Detection which is an important constituent that is employed to monitor and analyse the network traffic for recognizing and responding to intrusive or suspicious behavior. Innovative methods such as deep learning (DL) are employed to enhance the effectiveness of Intrusion Detection Systems (IDSs). DL is extremely implemented for IDS owing to its proficiency for automatically learning and extracting complex patterns and features from massive and multifaceted network datasets. Neural network (NN) models, permit the system to distinguish between anomalous patterns and normal network behaviors, increasing the accuracy of intrusion detection. The flexibility of DL methods to emerging cyberattacks with their adeptness to handle large - scale and various data, positions them as a strong and efficient tool for proactive and intelligent intrusion detection in existing cybersecurity settings. This article presents a Sine Cosine Algorithm with Optimal Convolutional Autoencoder for Intrusion Detection and Classification (SCAOCAE - IDC) method. The developed SCAOCAE - IDC system presents a wide - ranging strategy to improve the precision and effectiveness of IDSs. The method combines diverse advanced mechanisms like Min - Max scalar normalization for data preprocessing, Sine Cosine Algorithm (SCA) for feature selection (FS), Convolutional Autoencoder (CAE) for better feature extraction and classification, and Heap - Based Optimization (HBO) for hyperparameter tuning. The Min - Max scalar makes sure of robust data normalization, SCA increasingly chooses main features, CAE capably captures complex patterns in the data, and HBO fine - tunes hyperparameters for improved system performance. By employing the synergistic combination of such modules, the presented SCAOCAE - IDC algorithm indicates considerable outcomes for increasing the reliability and accuracy of IDSs and classification systems.

A survey on feature extraction and learning techniques for link prediction in homogeneous and heterogeneous complex networks

Complex networks are commonly observed in several real-world areas, such as social, biological, and technical systems, where they exhibit complicated patterns of connectedness and organised clusters. These networks have intricate topological characteristics that frequently elude conventional characterization. Link prediction in complex networks, like data flow in telecommunications networks, protein interactions in biological systems, and social media interactions on platforms like Facebook, etc., is an essential element of network analytics and presents fresh research challenges. Consequently, there is a growing emphasis in research on creating new link prediction methods for different network applications. This survey investigates several strategies related to link prediction, ranging from feature extraction based to feature learning based techniques, with a specific focus on their utilisation in dynamic and developing network topologies. Furthermore, this paper emphasises on a wide variety of feature learning techniques that go beyond basic feature extraction and matrix factorization. It includes advanced learning-based algorithms and neural network techniques specifically designed for link prediction. The study also presents evaluation results of different link prediction techniques on homogeneous and heterogeneous network datasets, and provides a thorough examination of existing methods and potential areas for further investigation.

Improved identification of network anomalies through optimal CURE clustering

Abstract In this paper, we propose an advanced network anomaly behavior identification framework to overcome the constraints inherent in conventional rule- or signature-based approaches, which often struggle with emerging and previously unknown threats. Central to our framework is an Enhanced CURE (Cluster Updating and REfining) clustering algorithm, meticulously tailored and refined to incorporate a density-based methodology. This enhancement enables the algorithm to discern subtle shifts in network anomaly patterns with heightened precision. The implementation workflow commences with the application of the optimized CURE algorithm to analyze network data, followed by the deployment of a sophisticated anomaly degree ranking mechanism. This mechanism, through meticulous calculation of individual data points' anomaly degrees and subsequent ranking, effectively isolates those deviating significantly from standard behavioral norms, incorporating a strategic threshold to filter out false positives. To validate our methodology's efficacy and its superiority over existing techniques, experiments were conducted utilizing a substantial real-world network dataset. These tests affirm not only a marked increase in the accuracy of abnormal behavior recognition and a reduction in computational intricacy but also demonstrate the adaptability across diverse network ecosystems. Our approach has proven successful in pinpointing a wide array of network anomalies, encompassing malicious cyberattacks, fraudulent activities, unauthorized intrusions, and breaches of security protocols, thereby highlighting its comprehensive capability in bolstering network defense strategies. Despite the notable advancements and successful identification of various network anomalies, our framework currently lacks integration with real-time learning capabilities, limiting its immediate responsiveness to rapidly evolving attack patterns and necessitating ongoing research for dynamic updates and adaptive learning mechanisms.

Trustworthiness-Driven Graph Convolutional Networks for Signed Network Embedding

The problem of representing nodes in a signed network as low-dimensional vectors, known as signed network embedding (SNE), has garnered considerable attention in recent years. While several SNE methods based on graph convolutional networks (GCNs) have been proposed for this problem, we point out that they significantly rely on the assumption that the decades-old balance theory always holds in the real-world. To address this limitation, we propose a novel GCN-based SNE approach, named as TrustSGCN, which corrects for incorrect embedding propagation in GCN by utilizing the trustworthiness on edge signs for high-order relationships inferred by the balance theory. The proposed approach consists of three modules: (M1) generation of each node’s extended ego-network; (M2) measurement of trustworthiness on edge signs; and (M3) trustworthiness-aware propagation of embeddings. Specifically, TrustSGCN leverages topological information to measure trustworthiness on edge sign for high-order relationships inferred by balance theory. It then considers structural properties inherent to an input network, such as the ratio of triads, to correct for incorrect embedding propagation. Furthermore, TrustSGCN learns the node embeddings by leveraging two well-known social theories, i.e., balance and status, to jointly preserve the edge sign and direction between nodes connected by existing edges in the embedding space. The experiments on six real-world signed network datasets demonstrate that TrustSGCN consistently outperforms six state-of-the-art GCN-based SNE methods. The code is available at https://github.com/kmj0792/TrustSGCN .

IMUNE: A novel evolutionary algorithm for influence maximization in UAV networks

In a network, influence maximization addresses identifying an optimal set of nodes to initiate influence propagation, thereby maximizing the influence spread. Current approaches for influence maximization encounter limitations in accuracy and efficiency. Furthermore, most existing methods are aimed at the IC (Independent Cascade) diffusion model, and few solutions concern dynamic networks. In this study, we focus on dynamic networks consisting of UAV (Unmanned Aerial Vehicle) clusters that perform coverage tasks and introduce IMUNE, an evolutionary algorithm for influence maximization in UAV networks. We first generate dynamic networks that simulate UAV coverage tasks and give the representation of dynamic networks. Novel fitness functions in the evolutionary algorithm are designed to estimate the influence ability of a set of seed nodes in a dynamic process. On this basis, an integrated fitness function is proposed to fit both the IC and SI (Susceptible–Infected) models. IMUNE can find seed nodes for maximizing influence spread in dynamic UAV networks with different diffusion models through the improvements in fitness functions and search strategies. Experimental results on UAV network datasets show the effectiveness and efficiency of the IMUNE algorithm in solving influence maximization problems.

Research on the Delineation Method of Urban Community Living Circle Based on Transportation Network Analysis in Yuanping, China

In the context of accelerating global urbanization and the demands for high-quality and sustainable development, the exploration of an urban community living area delineation method based on traffic network analysis offers a fresh perspective for defining urban living areas. This paper employs a traffic network analysis method rooted in objective analysis. It leverages open-source big data on Points of Interest (POI) from public facilities and road network data obtained from relevant urban planning to construct a comprehensive road network dataset for the central urban area. Following the construction of the road network dataset, the paper conducts a service area and accessibility analysis of public facilities, which serves as an initial step in outlining the boundaries of the urban community living area. Subsequently, the delineation is further refined by considering factors such as development boundaries, as well as natural and man-made constraints such as rivers, railways, and major roads. The boundaries of the urban community living area undergo further adjustments, taking into account the scope of the development boundary and various constraining elements such as rivers, railways, and main roads. A final revision is made by considering subjective factors, where the boundaries of the ten-minute urban community living area are ultimately determined through extensive communication and coordination with various stakeholders. This approach is aimed at meeting the current societal development needs, which include breaking down segregation, fostering social interactions, strengthening neighbourly relationships, enhancing overall quality of life, promoting sustainable development, and creating a more humane and sustainable city. Its ultimate goal is to enable residents to feel a sense of belonging and happiness within the bustling urban environment.

A specialized inclusive road dataset with elevation profiles for realistic pedestrian navigation using open geospatial data and deep learning

Built environment characteristics can greatly influence pedestrians' route choices with factors beyond distance, such as accessibility, convenience, safety, and aesthetics, playing crucial roles. Although current navigation apps, such as Google Maps and Waze, have successfully provided driving directions, their navigation services are insufficient and sometimes unrealistic for addressing pedestrians' needs, largely due to the lack of dedicated pedestrian networks and the associated navigation algorithms. To address the research gaps, this paper proposes a novel approach that integrates freely available geospatial data and computer vision technology to create a specialized inclusive network dataset for outdoor pedestrian navigation. Moreover, a pedestrian navigation algorithm is developed to generate more practical “shortest” and “alternative” paths by incorporating various sidewalk attributes. We applied the method to create a pedestrian navigation network in Las Vegas. SpaceNet's open imagery dataset was used to extract Las Vegas's road networks. A virtual audit process assessed the visual and operational properties of the sidewalk networks using Google street-level images, evaluating factors including sidewalk presence, widths, surface types and conditions, missing curb ramps, greenery, protection from weather conditions, and lighting. Google Earth's open elevation data were used to analyze road elevation profiles as meaningful 3D indicators of sidewalk accessibility for wheelchair users. Further, additional geometric properties of the network, including road curviness, proximity to road intersections, and directional changes, were detected and analyzed. A navigation experiment conducted with individuals having varying mobility abilities, including regular pedestrians, older adults, and wheelchair users demonstrated the effectiveness of the newly developed network and algorithm in meeting the diverse needs of pedestrians.

Network Data Intrusion Detection and Data Feature Extraction of Electromechanical Facilities from Machine Learning

With the rapid development of Internet technology, network security issues have become more complex and changeable. Various intrusion methods threaten the information network environment in the Electromechanical Facility (EF) system. This paper focuses on EF to study the relevant detection methods and data feature extraction in complex network intrusions. Firstly, four common machine learning algorithms are used to calculate the data set. The advantages and disadvantages of each algorithm are analyzed after tuning and comparison. Secondly, a network intrusion detection algorithm is proposed based on Recursive Feature Elimination (RFE) principal component analysis. It uses RFE to reduce the number of features and improve the elimination judgment index to align with the detection requirements of information network datasets. Finally, a fault diagnosis method is proposed based on empirical pattern decomposition and support vector machine under Renyi entropy complexity measurement. This method trains and identifies the Renyi entropy of several basic pattern components obtained by decomposing empirical patterns as feature vectors. The results show that the RFE method judged by random forest removes irrelevant features, and the evaluation index is improved to align with the network dataset’s detection requirements. It reduces the data dimension, reduces the operation time, and improves the accuracy of a few attack types. The comprehensive final detection effect is better than other algorithms. Additionally, the embedded operating system construction method based on the protection mechanism realizes the separate storage of the operating system and key data. Also, it can prevent the network system from being maliciously invaded, ensuring the stability of the instrument operation under harsh working conditions.

Methods for Corrosion Detection in Pipes Using Thermography: A Case Study on Synthetic Datasets

This study reviews advanced methods for corrosion detection and characterization in pipes using thermography, with a focus on addressing the limitations posed by small datasets. Thermography captures temperature distributions on the surface of pipes to identify subsurface defects. The challenges of sequential data processing, neural network performance, feature extraction, and dataset size are discussed, with proposed solutions such as advanced algorithms, feature selection techniques, and data augmentation. Given the significant gap in the current literature, there is a need for larger, more diverse datasets to train more robust and accurate machine learning models. A case study combining experimental data with Finite Element Method (FEM) simulations demonstrates that augmenting datasets with synthetic data significantly improves defect detection accuracy. These findings highlight the potential of integrating thermography with machine learning to enhance defect detection, providing insights for future research and practical applications.

Size-fixed group discovery via multi-constrained graph pattern matching

Multi-Constrained Graph Pattern Matching (MC-GPM) aims to match a pattern graph with multiple attribute constraints on its nodes and edges, and has garnered significant interest in various fields, including social-based e-commerce and trust-based group discovery. However, the existing MC-GPM methods do not consider situations where the number of each node in the pattern graph needs to be fixed, such as finding experts group with expert quantities and relations specified. In this paper, a Multi-Constrained Strong Simulation with the Fixed Number of Nodes (MCSS-FNN) matching model is proposed, and then a Trust-oriented Optimal Multi-constrained Path (TOMP) matching algorithm is designed for solving it. Additionally, two heuristic optimization strategies are designed, one for combinatorial testing and the other for edge matching, to enhance the efficiency of the TOMP algorithm. Empirical experiments are conducted on four real social network datasets, and the results demonstrate the effectiveness and efficiency of the proposed algorithm and optimization strategies.

Economic and environmental benefits of optimized waste transportation routes in Khulna

Urban transportation is a big source of pollution and greenhouse gas emissions. Khulna City handles the waste of 1.23 million people daily, using Heavy Duty Diesel Vehicles (HDDV) that release major environmental pollutants. The current waste transportation routes lack proper planning, leading to extra fuel consumption and pollutant emissions. This study aims to reduce fuel consumption and socio-environmental costs by improving waste transportation routes. Present collection routes, collecting points, and the speed of 30 waste collector vehicles were tracked using GPS devices for ten months between July 2023 and April 2024. The network dataset was modified according to four types of waste collector vehicles. ArcGIS Pro was used to find the optimal paths and their lengths. Fuel usage and prices were estimated using simple fuel consumption rate calculations. The lengths of current and optimal routes were used in COPERT to measure pollutant emissions. The results show that improved routes lower fuel consumption costs by approximately USD 55.39 per day and CO2 emissions by about 38.242 tonnes per year. Reductions in CO, CH4, NMVOC, NO2, PM10, and PM2.5 were roughly 9.3%, 9.53%, 9.21%, 9.29%, 9.35%, and 9.3%, respectively. This study demonstrates a comprehensive approach for improving solid waste management covering both financial efficiency and environmental effects.

Research on satellite structural health monitoring based on ultrashort femtosecond grating array and artificial neural network

The safety of spacecraft and satellite in orbit is very important, and structural health monitoring is needed. At present, the existing technology is limited by load and difficult to realize. In this paper, we propose a feasible method to detect and locate the damage of satellite by combining ultrashort femtosecond grating array inscribed on oxide-doped fiber with multilayer artificial neural network. An oxide-doped fiber with high robustness is designed, and ultrashort grating arrays are fabricated on the fiber by femtosecond laser point-by-point writing technology. The effects of impactor velocity and angle on impact response was investigated by numerical simulations and physical experiments. Subsequently, repeated impact experiments were conducted on the satellite to obtain the training dataset and testing dataset for two-dimensional convolutional neural network. The network with symmetric convention kernels has an 88.12% localization accuracy and a better performance in boundary region, and the network architecture with asymmetric convention kernels has a 90.31% accuracy and a better performance in middle region.

Study on Fast Temporal Prediction Method of Flame Propagation Velocity in Methane Gas Deflagration Experiment Based on Neural Network

To address the challenges of high experimental costs, complexity, and time consumption associated with pre-mixed combustible gas deflagration experiments under semi-open space obstacle conditions, a rapid temporal prediction method for flame propagation velocity based on Ranger-GRU neural networks is proposed. The deflagration experiment data are employed as the training dataset for the neural network, with the coefficient of determination (R2) and mean squared error (MSE) used as evaluation metrics to assess the predictive performance of the network. First, 108 sets of pre-mixed methane gas deflagration experiments were conducted, varying obstacle parameters to investigate methane deflagration mechanisms under different conditions. The experimental results demonstrate that obstacle-to-ignition source distance, obstacle shape, obstacle length, obstacle quantity, and thick and fine wire mesh obstacles all significantly influence flame propagation velocity. Subsequently, the GRU neural network was trained, and different activation functions (Sigmoid, Relu, PReLU) and optimizers (Lookahead, RAdam, Adam, Ranger) were incorporated into the backpropagation updating process of the network. The training results show that the Ranger-GRU neural network based on the PReLU activation function achieves the highest mean R2 value of 0.96 and the lowest mean MSE value of 7.16759. Therefore, the Ranger-GRU neural network with PReLU activation function can be a viable rapid prediction method for flame propagation velocity in pre-mixed methane gas deflagration experiments under semi-open space obstacle conditions.

Accurate segmentation of intracellular organelle networks using low-level features and topological self-similarity.

Intracellular organelle networks (IONs) such as the endoplasmic reticulum (ER) network and the mitochondrial (MITO) network serve crucial physiological functions. The morphology of these networks plays a critical role in mediating their functions. Accurate image segmentation is required for analyzing the morphology and topology of these networks for applications such as molecular mechanism analysis and drug target screening. So far, however, progress has been hindered by their structural complexity and density. In this study, we first establish a rigorous performance baseline for accurate segmentation of these organelle networks from fluorescence microscopy images by optimizing a baseline U-Net model. We then develop the multi-resolution encoder (MRE) and the hierarchical fusion loss (Lhf) based on two inductive components, namely low-level features and topological self-similarity, to assist the model in better adapting to the task of segmenting IONs. Empowered by MRE and Lhf, both U-Net and Pyramid Vision Transformer (PVT) outperform competing state-of-the-art models such as U-Net++, HR-Net, nnU-Net, and TransUNet on custom datasets of the ER network and the MITO network, as well as on public datasets of another biological network, the retinal blood vessel network. In addition, integrating MRE and Lhf with models such as HR-Net and TransUNet also enhances their segmentation performance. These experimental results confirm the generalization capability and potential of our approach. Furthermore, accurate segmentation of the ER network enables analysis that provides novel insights into its dynamic morphological and topological properties. Code and data are openly accessible at https://github.com/cbmi-group/MRE.

Copula Approximate Bayesian Computation Using Distribution Random Forests

Ongoing modern computational advancements continue to make it easier to collect increasingly large and complex datasets, which can often only be realistically analyzed using models defined by intractable likelihood functions. This Stats invited feature article introduces and provides an extensive simulation study of a new approximate Bayesian computation (ABC) framework for estimating the posterior distribution and the maximum likelihood estimate (MLE) of the parameters of models defined by intractable likelihoods, that unifies and extends previous ABC methods proposed separately. This framework, copulaABCdrf, aims to accurately estimate and describe the possibly skewed and high-dimensional posterior distribution by a novel multivariate copula-based meta-t distribution based on univariate marginal posterior distributions that can be accurately estimated by distribution random forests (drf), while performing automatic summary statistics (covariates) selection, based on robustly estimated copula dependence parameters. The copulaABCdrf framework also provides a novel multivariate mode estimator to perform MLE and posterior mode estimation and an optional step to perform model selection from a given set of models using posterior probabilities estimated by drf. The posterior distribution estimation accuracy of the ABC framework is illustrated and compared with previous standard ABC methods through several simulation studies involving low- and high-dimensional models with computable posterior distributions, which are either unimodal, skewed, or multimodal; and exponential random graph and mechanistic network models, each defined by an intractable likelihood from which it is costly to simulate large network datasets. This paper also proposes and studies a new solution to the simulation cost problem in ABC involving the posterior estimation of parameters from datasets simulated from the given model that are smaller compared to the potentially large size of the dataset being analyzed. This proposal is motivated by the fact that, for many models defined by intractable likelihoods, such as the network models when they are applied to analyze massive networks, the repeated simulation of large datasets (networks) for posterior-based parameter estimation can be too computationally costly and vastly slow down or prohibit the use of standard ABC methods. The copulaABCdrf framework and standard ABC methods are further illustrated through analyses of large real-life networks of sizes ranging between 28,000 and 65.6 million nodes (between 3 million and 1.8 billion edges), including a large multilayer network with weighted directed edges. The results of the simulation studies show that, in settings where the true posterior distribution is not highly multimodal, copulaABCdrf usually produced similar point estimates from the posterior distribution for low-dimensional parametric models as previous ABC methods, but the copula-based method can produce more accurate estimates from the posterior distribution for high-dimensional models, and, in both dimensionality cases, usually produced more accurate estimates of univariate marginal posterior distributions of parameters. Also, posterior estimation accuracy was usually improved when pre-selecting the important summary statistics using drf compared to ABC employing no pre-selection of the subset of important summaries. For all ABC methods studied, accurate estimation of a highly multimodal posterior distribution was challenging. In light of the results of all the simulation studies, this article concludes by discussing how the copulaABCdrf framework can be improved for future research.