Graph Data Research Articles

ADDRESSING WATER SCARCITY THROUGH STATISTICAL INQUIRY IN TEACHER EDUCATION

This article presents the design and implementation of a study and research path for teacher education (SRP-TE) based on the Anthropological Theory of the Didactic. The goal is to analyze this teacher education proposal for inclusive statistics education aiming to overcome constraints derived from the phenomenon of the transparency of data treatment. The proposal starts with a newspaper report about the loss of water resources in Brazil and questions the data supporting it. The study focuses on one of the participating teachers from a disadvantaged region in the Northeast, where she worked in a rural school with few resources and poor infrastructure. The course helped her implement an inquiry activity with her sixth-grade students and mobilize digital resources for data visualization and graph representations. This case study contributed to analyzing how the SRP-TE promoted teachers’ professional development and provided elements for teaching inclusive statistics.

Analysis of Pedestrian–Vehicle Interaction Dynamics at Signalized Urban Intersections: A Surrogate Safety Measure Approach

Increased pedestrian–vehicle interactions, especially at signalized intersection crosswalks, have resulted in more pedestrian fatalities, and this situation worsens under heterogeneous traffic conditions. Therefore, evaluating pedestrian road-crossing safety is crucial, especially at signalized intersection crosswalks. This article aims to study pedestrian crossing safety at signalized intersection crosswalks based on the safety margin. Video graphic data were collected from eight signalized intersections. Data were extracted, and significant variables influencing the pedestrian safety margin (PSM) were identified. A random-intercept multiple linear regression model for predicting the PSM was estimated. Data included site, demographic, behavioral, exposure, the state of the crossing (distraction), glance, and traffic characteristics as variables. The model results revealed that pedestrians used the largest safety margin against heavy vehicles while crossing in a group. Pedestrians’ crossing speed has a significant influence on the PSM. It was also found that pedestrians showed the highest level of caution (used the largest safety margin) against right-turning vehicles compared with through vehicles. The glance variable estimates revealed that the “during-crossing glance” is an important determinant of the PSM, while the “before-crossing glance” is insignificant. In addition, unsafe pedestrian crossing behavior concerning distractors highlighted that the use of headphones significantly influences the PSM. The results of the current PSM model could aid in the efficient design of future pedestrian infrastructure and suggest appropriate remedial measures for existing intersection crosswalks to enhance pedestrian safety.

ANALYSIS OF STRENGTH AND STIFFNESS OF PERMANENT FORMWORK BLOCKS WITH A WIDTH OF 300 TO 400 MM FOR LOW-RISE CONSTRUCTION

The article investigates the structural performance of concrete blocks used as permanent formwork in low-rise construction, with widths ranging from 300 to 400 mm. These blocks serve as both formwork and part of the structural system, providing a durable solution for wall construction. In Ukraine, the adoption of such blocks is limited due to underdeveloped reinforcement methodologies, which complicates their application in construction projects. The authors examine the strength and stiffness of a standard block with dimensions of 500×400×200 mm, using software-based modeling in TechEditor to streamline the calculations. This research produces graphical data on load-bearing capacity and bending stiffness, which designers can use to configure reinforced concrete walls with these blocks. The study also offers practical reinforcement guidance, filling gaps in current standards and assisting engineers in implementing these blocks effectively. Permanent formwork blocks, common internationally, typically contain voids and channels that facilitate rebar installation, creating a monolithic structure after the concrete sets. However, due to inconsistencies in reinforcement advice from manufacturers, Ukrainian engineers often resort to custom approaches or traditional monolithic construction. This study, therefore, aims to address these challenges by providing structured reinforcement recommendations. The research includes load-bearing and stiffness calculations for walls with variable depth (300-400 mm), accounting for different rebar diameters to simulate the range of possible configurations. Findings demonstrate that using blocks with rebar yields significant material savings (approximately 33% less concrete) compared to solid walls, without proportionate strength loss, making them a cost-effective choice for low-rise construction. In conclusion, the article offers engineers and manufacturers valuable insights into the practical use of permanent formwork blocks, presenting a foundation for further research into optimization and broader applications. Keywords: reinforced concrete, block, formwork, reinforcement, analysis.

HybridGNN: A Self-Supervised Graph Neural Network for Efficient Maximum Matching in Bipartite Graphs

Solving maximum matching problems in bipartite graphs is critical in fields such as computational biology and social network analysis. This study introduces HybridGNN, a novel Graph Neural Network model designed to efficiently address complex matching problems at scale. HybridGNN leverages a combination of Graph Attention Networks (GATv2), Graph SAGE (SAGEConv), and Graph Isomorphism Networks (GIN) layers to enhance computational efficiency and model performance. Through extensive ablation experiments, we identify that while the SAGEConv layer demonstrates suboptimal performance in terms of accuracy and F1-score, configurations incorporating GATv2 and GIN layers show significant improvements. Specifically, in six-layer GNN architectures, the combinations of GATv2 and GIN layers with ratios of 4:2 and 5:1 yield superior accuracy and F1-score. Therefore, we name these GNN configurations HybridGNN1 and HybridGNN2. Additionally, techniques such as mixed precision training, gradient accumulation, and Jumping Knowledge networks are integrated to further optimize performance. Evaluations on an email communication dataset reveal that HybridGNNs outperform traditional algorithms such as the Hopcroft–Karp algorithm, the Hungarian algorithm, and the Blossom/Edmonds’ algorithm, particularly for large and complex graphs. These findings highlight HybridGNN’s robust capability to solve maximum matching problems in bipartite graphs, making it a powerful tool for analyzing large-scale and intricate graph data. Furthermore, our study aligns with the goals of the Symmetry and Asymmetry Study in Graph Theory special issue by exploring the role of symmetry in bipartite graph structures. By leveraging GNNs, we address the challenges related to symmetry and asymmetry in graph properties, thereby improving the reliability and fault tolerance of complex networks.

Variational graph neural network with diffusion prior for link prediction

Recently, Graph neural networks(GNNs) has achieved tremendous success in a variety of fields. Many approaches have been proposed to address data with graph structure. However, many of these are deterministic methods, therefore, they are unable to capture the uncertainty, which is inherent in the nature of graph data. Various VAE(Variational auto-encoder)-based approaches have been proposed to tackle such problems. Unfortunately, due to the simple a posterior and a prior assumption problems of such methods, they are not well suited to handle uncertainty in graph data. For example, VGAE(Variational graph auto-encoder) assumes that the posterior and prior distributions are simple Gaussian distributions, which can lead to overfitting problems when incompatible with the true distributions. Many methods propose to solve the posterior distribution problem, but most ignore the effect of the prior distribution. Therefore, in this paper, we proposed a novel method to solve the Gaussian prior problem. Specifically, in order to enhance the representation power of the prior distribution, we use the diffusion model to model the prior distribution. We incorporate the diffusion model into VGAE. In the forward diffusion process, noise is gradually added to the latent variables, and then the samples are recovered by the backward diffusion process. To realize the backward diffusion process, we propose a new denoising model which predicts noise by stacking GCN(Graph Convolution Network) and MLP(Multi-layers Perceptron). We perform experiments on different datasets and the experimental results demonstrate that our method obtains state-of-the-art results.

Unified representation aggregated from graph and global features for multi-source data clustering

Multi-source data has received increasing attention due to its excellent performance in clustering tasks. However, existing multi-source data clustering methods utilize shallow graph learning methods to model similarity graphs of multi-source data, and ignore the importance of weak connections between samples within the same cluster. Thus, these connections fail to be explored in the global similarity graph of multi-source data. In this paper, we proposed a unified representation aggregated from graph and global features (UGGF) method for multi-source data clustering. Specifically, it utilizes the cross-source graph diffusion process to preserve invariant connections in multi-source similarity graphs and preserve weak connections between samples through their connection relationships between different sources. Furthermore, inspired by self-attention, the encoder of transformers is used to learn multi-source global feature representation. Then, global features and similarity graphs are integrated to comprehensively explore the multi-source data, aiming to obtain a unified representation for the final clustering task. The proposed UGGF method is validated on four benchmark datasets. Extensive experimental results demonstrate the superiority of the proposed method compared with other state-of-the-art multi-source data clustering methods.

Algorithms for graph theory matching problems based on computer science

Existing graph-matching algorithms only use the graph’s edges to transmit information and cannot perform hierarchical reasoning and fusion. Although they have achieved good results in graph matching, problems exist such as planarization and insufficient representation of graph data. This paper aims to study graph theory matching algorithms based on computer science, solve matching problems on large-scale graphs, reduce computation time, and improve solving efficiency. This paper studied graph theory matching algorithms based on computer science, including heuristic algorithm-based matching algorithms and machine learning-based matching algorithms; the specific matching problem was mathematically analyzed and transformed into a matching problem in graph theory, which included defining the input and output of the problem, determining the structure and properties of nodes and edges in the graph, and clarifying the required matching and constraint conditions. The experimental results of this paper showed that the average optimal matching rates of the Kuhn–Munkres algorithm, Gale–Shapley (GS)-based algorithm, Genetic Algorithm (GA), Particle Swarm Optimization (PSO) algorithm and Support Vector Machine (SVM) algorithm in complex scenarios were 62.05%, 58.42%, 82.79%, 81.99% and 83.50%, respectively. Studying graph theory matching algorithms based on computer science is of great significance. It can not only solve practical application problems and improve computational efficiency, but also promote algorithm optimization, which helps to improve the processing speed and efficiency of practical problems.

Privacy-preserving local clustering coefficient query on structured encrypted graphs

Graphs and graph databases serve as the fundamental building blocks for various network structures. In real-world network scenarios, nodes often aggregate due to their approximate organizational associations with each other. The local clustering coefficient, which evaluates the proximity of nodes within a graph, plays an important role in quantifying the structural properties of graphs in scrutinizing network robustness and understanding its intricate dynamics. Despite the growing popularity of easily accessible cloud services among small and medium-sized enterprises as well as individuals, the potential risk of data privacy disclosure when outsourcing large graphs to third-party servers is increasing. It is vital to explore a technique for executing queries on encrypted graph data. In this paper, we propose a structured encryption scheme to achieve privacy-preserving local clustering coefficient query (STE-CC) on the outsourced encrypted graphs. To calculate the clustering coefficient, we design the PSIsum protocol to sum the number of intersections, in which the basic private set intersection (PSI) protocol combines Bloom filter (BF) and garbled Bloom filter (GBF) to perform the private matching for counting the number of common neighbors. When configured with appropriate parameters, it can achieve no false negatives and negligible false positives. Finally, the security analysis and experimental evaluation on real-world graph data substantiate the effectiveness and efficiency of our approach.

Hierarchically Recognizing Vector Graphics and A New Chart-Based Vector Graphics Dataset.

The conventional approach to image recognition has been based on raster graphics, which can suffer from aliasing and information loss when scaled up or down. In this paper, we propose a novel approach that leverages the benefits of vector graphics for object localization and classification. Our method, called YOLaT (You Only Look at Text), takes the textual document of vector graphics as input, rather than rendering it into pixels. YOLaT builds multi-graphs to model the structural and spatial information in vector graphics and utilizes a dual-stream graph neural network (GNN) to detect objects from the graph. However, for real-world vector graphics, YOLaT only models in flat GNN with vertexes as nodes ignore higher-level information of vector data. Therefore, we propose YOLaT++ to learn Multi-level Abstraction Feature Learning from a new perspective: Primitive Shapes to Curves and Points. On the other hand, given few public datasets focus on vector graphics, data-driven learning cannot exert its full power on this format. We provide a large-scale and challenging dataset for Chart-based Vector Graphics Detection and Chart Understanding, termed VG-DCU, with vector graphics, raster graphics, annotations, and raw data drawn for creating these vector charts. Experiments show that the YOLaT series outperforms both vector graphics and raster graphics-based object detection methods on both subsets of VG-DCU in terms of both accuracy and efficiency, showcasing the potential of vector graphics for image recognition tasks.

A Novel TOPSIS Framework for Multi-Criteria Decision Making with Random Hypergraphs: Enhancing Decision Processes

In today’s complex decision-making landscape, multi-criteria decision-making (MCDM) frameworks play a crucial role in managing conflicting criteria. Traditional MCDM methods often face challenges due to uncertainty and interdependencies among criteria. This paper presents a novel framework that combines the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) with random hypergraphs to enhance decision processes. In TOPSIS, asymmetry in criterion interactions is typically managed by assigning different weights, while for independent criteria, Euclidean distance introduces geometric symmetry, treating all dimensions (criteria) equally when calculating an alternative’s distance from ideal or negative-ideal solutions. Although assigning weights can partially address asymmetry caused by interdependencies and uncertainties among criteria, it cannot fully account for uncertainty in data and criteria interactions. Our approach integrates random hypergraphs to better capture these relationships, offering a more refined representation of decision problems and improving the robustness of the decision-making process. In this method, we first capture criteria interactions in a random hypergraph. Using properties of the graph and input data, the algorithm then generates weights for interacted groups of criteria. These weights, termed “dynamic weights”, adapt in response to changes in criteria interactions and data, forming the basis for a generalized TOPSIS algorithm. A comparative study with illustrative examples highlights the advantages of this enhanced TOPSIS framework, showing how random hypergraphs expand its analytical capabilities. This research advances the theoretical foundation of MCDM frameworks while offering practical insights for practitioners seeking robust solutions in complex and uncertain decision environments.

IGCN: A Provably Informative GCN Embedding for Semi-Supervised Learning With Extremely Limited Labels.

Graph Neural Networks (GNNs) have gained much more attention in the representation learning for the graph-structured data. However, the labels are always limited in the graph, which easily leads to the overfitting problem and causes the poor performance. To solve this problem, we propose a new framework called IGCN, short for Informative Graph Convolutional Network, where the objective of IGCN is designed to obtain the informative embeddings via discarding the task-irrelevant information of the graph data based on the mutual information. As the mutual information for irregular data is intractable to compute, our framework is optimized via a surrogate objective, where two terms are derived to approximate the original objective. For the former term, it demonstrates that the mutual information between the learned embeddings and the ground truth should be high, where we utilize the semi-supervised classification loss and the prototype based supervised contrastive learning loss for optimizing it. For the latter term, it requires that the mutual information between the learned node embeddings and the initial embeddings should be high and we propose to minimize the reconstruction loss between them to achieve the goal of maximizing the latter term from the feature level and the layer level, which contains the graph encoder-decoder module and a novel architecture GCN Info. Moreover, we provably show that the designed GCN Info can better alleviate the information loss and preserve as much useful information of the initial embeddings as possible. Experimental results show that the IGCN outperforms the state-of-the-art methods on 7 popular datasets.

GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation.

Source-free domain adaptation is a crucial machine learning topic, as it contains numerous applications in the real world, particularly with respect to data privacy. Existing approaches predominantly focus on Euclidean data, such as images and videos, while the exploration of non-Euclidean graph data remains scarce. Recent graph neural network (GNN) approaches could suffer from serious performance decline due to domain shift and label scarcity in source-free adaptation scenarios. In this study, we propose a novel method named Graph Diffusion-based Alignment with Jigsaw (GALA) tailored for source-free graph domain adaptation. To achieve domain alignment, GALA employs a graph diffusion model to reconstruct source-style graphs from target data. Specifically, a score-based graph diffusion model is trained using source graphs to learn the generative source styles. Then, we introduce perturbations to target graphs via a stochastic differential equation instead of sampling from a prior, followed by the reverse process to reconstruct source-style graphs. We feed them into an off-the-shelf GNN and introduce class-specific thresholds with curriculum learning, which can generate accurate and unbiased pseudo-labels for target graphs. Moreover, we develop a simple yet effective graph mixing strategy named graph jigsaw to combine confident graphs and unconfident graphs, which can enhance generalization capabilities and robustness via consistency learning. Extensive experiments on benchmark datasets validate the effectiveness of GALA. The source code is available at https://github.com/luo-junyu/GALA.

Dynamic Graphical Models with Variable Selection for Effective Connectivity

This paper proposes a novel approach that combines dynamic linear models applied to graph data and variable selection through spike-and-slab priors. The new class of models, called Dynamic Graphical Variable Selection, is used to infer effective connectivity in certain brain regions allowing both connectivity weights and graphical structure to vary over time. One advantage of our method is that as the graphical structure is estimated inferentially, the computational cost is reduced. That way our methodology can accommodate high-dimensional data, such as large networks observed through long periods of time. We illustrate our methodology via numerical experiments with simulated and synthetic data, and then applied to fNIRS real data. The obtained results showed that the static version of our model is competitive against previous methodologies and demands a lower computational cost. Our model is more flexible than the previous methodologies by allowing the graphical structure to vary over time.

Tilde, an interdisciplinary data access solution serving GeoNet’s volcano and other hazard data

Tilde is a new in-house developed solution that the GNS Science’s GeoNet program has recently developed to provide storage and access to low sample rate datasets used to monitor tsunami, landslides, and volcanoes in Aotearoa New Zealand. It includes datasets covering sample rates of 15 s or longer. Time series data are stored and disseminated in JSON and CSV formats, and users can access these through an application programming interface (API) and through graphical user interfaces (GUIs). Tilde’s GUIs were created to allow technical and non-technical users easy access to the available data. The introduction of the Tilde system as one of the GeoNet program delivery channels has represented a big step forward for GeoNet’s volcano data holdings by providing a single point to access all low to medium-sample rate volcano-specific monitoring data. We designed the system and developed a domain model, an API, a graphical data discovery interface, and associated data tutorials. This work leverages the open-by-default data policy for data generated through the GeoNet program. This paper is intended to highlight how we made many of the key decisions that shaped the Tilde system, how they were impacted by our multi-hazard monitoring requirements, and how they have improved access to volcano monitoring data. We conclude with some open questions about the need to develop common standards to share analysis-ready time series data within different disciplines in volcanology and geophysics.

GraphSense: a self-aware dynamic graph learning networks for graph data over internet

GraphSense: a self-aware dynamic graph learning networks for graph data over internet

ACCELERATING IMAGE PROCESSING USING PARALLEL COMPUTATIONS IN OPENMP: DEVELOPMENT AND PERFORMANCE ANALYSIS OF A GRAPHICS EDITOR

In today’s digital world, image processing plays a crucial role in various aspects of human life. From creating visual content for social media to analyzing medical images, powerful tools for image manipulation are in constant demand. The growing requirements for image quality and processing speed make the search for efficient methods to accelerate these processes highly relevant. This paper investigates the development and implementation of a graphics editor that utilizes OpenMP parallel computing to accelerate data processing. This technology enables the efficient distribution of computational tasks across multiple processor cores, significantly improving system performance. The developed software offers a set of popular graphic effects, including negative, grayscale, sepia, blur, sharpening, and posterization. Each effect is implemented in both sequential and parallel modes using OpenMP, allowing for the comparison of different computational approaches. To evaluate the effectiveness of the proposed solution, a series of experiments were conducted on images of various sizes. These experiments involved applying each effect to images ranging from small icons to high-quality photographs. A comparative analysis of the efficiency of sequential and parallel computation methods demonstrated the significant advantages of the latter. The results of the study show a substantial acceleration of image processing when using OpenMP technology. This acceleration is particularly noticeable for computationally intensive effects such as blurring or sharpening, and when working with large images. In some cases, it was possible to achieve a significant increase in processing speed, opening up new possibilities for working with large volumes of graphic data. This research has significant practical value for software developers working on optimizing the performance of graphics editors and other image processing applications. It demonstrates how the application of modern parallel computing technologies can significantly improve the efficiency of working with graphic data, paving the way for the creation of more powerful and faster image processing tools.

D4A: An efficient and effective defense across agnostic adversarial attacks

Recent studies show that Graph Neural Networks (GNNs) are vulnerable to structure adversarial attacks, which draws attention to adversarial defenses in graph data. Previous defenses designed heuristic defense strategies for specific attacks or graph properties, and are no longer sufficiently robust across all these attacks. To address this problem, we discuss the abnormal behaviors of GNNs in structure perturbations from a posterior distribution perspective. We suggest that the structural vulnerability of GNNs stems from their dependence on local graph smoothing, which can also lead to unfitting — a first-found phenomenon specific to the graph domain. We demonstrate that abnormal behaviors, except for unfitting, can attribute to a posterior distribution shift. To intrinsically prevent the occurrence of abnormal behaviors, we first propose smooth-less message passing to enhance the tolerance with respect to structure perturbations, while significantly mitigating the unfitting. We also propose the distribution shift constraint to restrict other abnormal behaviors of our model. Our approach is evaluated on six different datasets across over four kinds of attacks and compared to 11 representative baselines. The experimental results show that our method improves the defense performance across various attacks, and provides a great trade-off between accuracy and adversarial robustness.

Multi-angle information aggregation for inductive temporal graph embedding.

Graph embedding has gained significant popularity due to its ability to represent large-scale graph data by mapping nodes to a low-dimensional space. However, most of the existing research in this field has focused on transductive learning, where fixed node embeddings are generated by training the entire graph. This approach is not well-suited for temporal graphs that undergo continuous changes with the addition of new nodes and interactions. To address this limitation, we propose an inductive temporal graph embedding method called MIAN (Multi-angle Information Aggregation Network). The key focus of MIAN is to design an aggregation function that combines multi-angle information for generating node embeddings. Specifically, we divide the information into different angles, including neighborhood, temporal, and environment. Each angle of information is modeled and mined independently, and then fed into an improved gated recuttent unit (GRU) module to effectively combine them. To assess the performance of MIAN, we conduct extensive experiments on various real-world datasets and compare its results with several state-of-the-art baseline methods across diverse tasks. The experimental findings demonstrate that MIAN outperforms these methods.

PRAGA: A Priority-Aware Hardware/Software Co-design for High-Throughput Graph Processing Acceleration

Graph processing is pivotal in deriving insights from complex data structures but faces performance limitations due to the irregular nature of graphs. Traditional general-purpose processors often struggle with low instruction-level parallelism and energy inefficiency when handling graph data. In response, modern graph accelerators have embraced an intra-edge-parallel model to enhance parallelization, significantly outperforming conventional processors. However, the indiscriminate processing of edges in existing systems results in substantial computational redundancy, negatively impacting overall efficiency. This paper introduces PRAGA, an innovative graph accelerator designed to optimize efficiency by selectively processing edges that significantly contribute to final results while preserving high computational parallelism. PRAGA utilizes an intra-edge-sequential model, prioritizing edge processing to capitalize on coarse-grained vertex-level parallelism and minimize unnecessary computations. It incorporates a hot-value manager to alleviate network-on-chip congestion and a memory-aware coalescer to minimize redundant data accesses. Our experimental results, obtained using a Xilinx Alveo U280 FPGA accelerator card, demonstrate that PRAGA achieves speedups of 17.88 × and 5.86 × over state-of-the-art accelerators ScalaGraph and GraphDyns, respectively, and outperforms the advanced GPU-based system Gunrock by 22.52 × on average. This substantial improvement underscores PRAGA’s potential to redefine performance benchmarks in graph processing.

Protective Effect of 1,8-Cineole (Eucalyptol) on Respiratory System: A Systematic Review and Meta-analysis from Animal Studies

Background 1,8-Cineole is used in traditional folk medicine to treat various diseases. This study evaluates the protective effects of 1,8-cineole on the respiratory system by investigating its impact on inflammatory factors in animal studies. Materials and Methods We conducted searches in PubMed, Medline, Embase, Cochrane, and the Web of Science databases until December 2023. This study utilized Get Data Graph Digitizer 2.26, EndNote, and RevMan 5.4. The random effects model and standard mean difference (SMD) were applied for data analysis. Results The results showed tumor necrosis factor-alpha (TNF-α) (SMD: −8.19, 95% CI: −11.30 to −5.08, p < 0.00001), interleukin (IL)-6 (SMD: −7.38, 95% CI: −10.61 to −4.15, p < 0.00001), IL-1β (SMD: −19.18, 95% CI: −32.57 to −5.79, p = 0.005), NF-κB (SMD: −6.26, 95% CI: −7.88 to −4.65, p < 0.00001), neutrophils (SMD: −8.16, 95% CI: −11.65 to −4.67, p < 0.00001), and macrophages (SMD: −5.06, 95% CI: −8.06 to −2.05, p = 0.001). Conclusion The study suggests that 1,8-cineole significantly inhibits the expression of inflammatory factors, indicating its potential for further study and development.