Traditional Graph Research Articles

Enabling Perspective-Aware Ai with Contextual Scene Graph Generation

This paper advances contextual image understanding within perspective-aware Ai (PAi), an emerging paradigm in human–computer interaction that enables users to perceive and interact through each other’s perspectives. While PAi relies on multimodal data—such as text, audio, and images—challenges in data collection, alignment, and privacy have led us to focus on enabling the contextual understanding of images. To achieve this, we developed perspective-aware scene graph generation with LLM post-processing (PASGG-LM). This framework extends traditional scene graph generation (SGG) by incorporating large language models (LLMs) to enhance contextual understanding. PASGG-LM integrates classical scene graph outputs with LLM post-processing to infer richer contextual information, such as emotions, activities, and social contexts. To test PASGG-LM, we introduce the context-aware scene graph generation task, where the goal is to generate a context-aware situation graph describing the input image. We evaluated PASGG-LM pipelines using state-of-the-art SGG models, including Motifs, Motifs-TDE, and RelTR, and showed that fine-tuning LLMs, particularly GPT-4o-mini and Llama-3.1-8B, improves performance in terms of R@K, mR@K, and mAP. Our method is capable of generating scene graphs that capture complex contextual aspects, advancing human–machine interaction by enhancing the representation of diverse perspectives. Future directions include refining contextual scene graph models and expanding multi-modal data integration for PAi applications in domains such as healthcare, education, and social robotics.

Heterogeneous Graph Embedding with Dual Edge Differentiation

Recently, heterogeneous graphs have attracted widespread attention as a powerful and practical superclass of traditional homogeneous graphs, which reflect the multi-type node entities and edge relations in the real world. Most existing methods adopt meta-path construction as the mainstream to learn long-range heterogeneous semantic messages between nodes. However, such schema constructs the node-wise correlation by connecting nodes via pre-computed fixed paths, which neglects the diversities of meta-paths on the path type and path range. In this paper, we propose a meta-path-based semantic embedding schema, which is called Heterogeneous Graph Embedding with Dual Edge Differentiation (HGE-DED) to adequately construct flexible meta-path combinations thus learning the rich and discriminative semantic of target nodes. Concretely, HGE-DED devises a Multi-Type and multi-Range Meta-Path Construction (MTR-MP Construction), which covers the comprehensive exploration of meta-path combinations from path type and path range, expressing the diversity of edges at more fine-grained scales. Moreover, HGE-DED designs the semantics and meta-path joint guidance, constructing a hierarchical short- and long-range relation adjustment, which constrains the path learning as well as minimizes the impact of edge heterophily on heterogeneous graphs. Experimental results on four benchmark datasets demonstrate the effectiveness of HGE-DED compared with state-of-the-art methods.

Machine learning approaches for predicting craniofacial anomalies with graph neural networks

This study explores the use of machine learning algorithms, including traditional approaches and graph neural networks (GNNs), to predict certain diseases by analyzing protein-protein interactions. Protein-protein interactions (PPIs) are complex, multifaceted, and sometimes ever-changing. Therefore, analyzing PPIs and making predictions based on them present significant challenges to traditional computational techniques. However, machine learning, particularly GNNs, with their powerful ability to identify complex patterns within large, convoluted datasets, emerge as compelling and revolutionary tools for unraveling these intricate biological networks. We apply machine learning, aided by SHAP explainability and GNNs, on three networks of distinct sizes, ranging from small to large. While the ML results highlight the higher importance of network features in prediction, GNNs exhibit superior accuracy.

Developing a Directed Graph Analysis Framework as a Method to Analyse and Present Complex Datasets: A Case Study in Tax Compliance

Directed graphs are often used as graphical representations of interrelationships between entities. In many fields of research besides the STEM fields, datasets containing complex qualitative interrelationships are challenging to represent graphically in traditional line graphs, bar graphs, or pie charts. In addition, if quantitative data needs to be presented on top of the qualitative relationships, graphical representation becomes even more complex. As a result, datasets of this nature are often tabulated or presented in text since graphical representation is considered difficult or impractical. This paper presents a Directed Graph Analysis Framework that may be used to develop graphical illustrations of such complex datasets. A PhD study in employer tax compliance undertaken by the principal author is utilised as a case study in this paper (Van der Walt, Z., 2024). The framework is then used to develop a variable interrelationship and compliance decision flow diagram to present employer tax compliance decisions in graphical form. It is demonstrated that the method is suitable to produce a single graphical representation of a large number of variables and sub-variables, displaying the relevant qualitative and quantitative information in an easy-to-understand way. The proposed method may be applied to other fields of research where similarly complex datasets are presented.

A Short Note for Hypersoft Rough Graphs

Graph theory, a branch of mathematics, explores relationships among entities using vertices and edges. To address the uncertainties inherent in real-world networks, Uncertain Graph Theory has emerged as a significant extension within this field. Hypersoft Graphs advance traditional graphs further by incorporating multi-attribute nodes, allowing each node to represent multiple attribute values, thus capturing more complex, multi-dimensional relationships. The Soft Rough Set and Soft Rough Graph combine the principles of Soft Sets and Rough Sets to manage uncertainty in a more refined manner. In this paper, we introduce the Hypersoft Rough Graph and analyze its relationships with other graph classes.

Antipodal Turiyam Neutrosophic Graphs

Graph theory, a mathematical field, investigates the relationships between entities through vertices and edges [29]. Within this discipline, Uncertain Graph Theory emerges to model uncertainties in realworld networks. This paper presents the concept of the Antipodal Turiyam Neutrosophic Graph. In an Antipodal Graph, two nodes are connected if their shortest path distance equals the graph's diameter, emphasizing connections between the farthest nodes. Turiyam Neutrosophic Graphs extend traditional graphs by introducing four membership values-truth, indeterminacy, falsity, and liberal state-assigned to each vertex and edge, enabling a more nuanced representation of complex relationships.

Modeling functional connectivity changes during an auditory language task using line graph neural networks.

Functional connectivity (FC) refers to the activation correlation between different brain regions. FC networks as typically represented as graphs with brain regions of interest (ROIs) as nodes and functional correlation as edges. Graph neural networks (GNNs) are machine learning architectures used to analyze FC graphs. However, traditional GNNs are limited in their ability to characterize FC edge attributes because they typically emphasize the importance of ROI node-based brain activation data. Line GNNs convert the edges of the original graph to nodes in the transformed graph, thereby emphasizing the FC between brain regions. We hypothesize that line GNNs will outperform traditional GNNs in FC applications. We investigated the performance of two common GNN architectures (GraphSAGE and GCN) trained on line and traditional graphs predicting task-associated FC changes across two datasets. The first dataset was from the Human Connectome Project (HCP) with 205 participants, the second was a dataset with 12 participants. The HCP dataset detailed FC changes in participants during a story-listening task, while the second dataset included the FC changes in a different auditory language task. Our findings from the HCP dataset indicated that line GNNs achieved lower mean squared error compared to traditional GNNs, with the line GraphSAGE model outperforming the traditional GraphSAGE by 18% (p < 0.0001). When applying the same models to the second dataset, both line GNNs also showed statistically significant improvements over their traditional counterparts with little to no overfitting. We believe this shows that line GNN models demonstrate promising utility in FC studies.

ELPGPT: Large Language Models Enhancing Link Prediction in Electrical Knowledge Graph

Graphs provide essential means for organizing and analyzing complex equipment data. Although link prediction techniques have been widely applied to enhance knowledge graphs, existing methods still show room for improvement in accuracy, especially when dealing with sparse data. To address this, we introduce ELPGPT (Large Language Models Enhancing Link Prediction in Electrical Equipment Knowledge Graph), a novel approach that integrates large language models into link prediction to enhance the accuracy of relation prediction within electrical equipment knowledge graphs. The core of the ELPGPT method lies in the combination of large language models with traditional knowledge graph link prediction techniques. By leveraging the deep semantic understanding capabilities of large language models, this method effectively extracts relational features and enhances the handling of sparse data. Additionally, we employ a Retrieval-Augmented Generation (RAG) approach, which, by integrating external data sources, further enhances the precision and relevance of predictions. Experiments on the Electrical Equipment Knowledge Graph (EEKG) demonstrate that ELPGPT significantly improves performance across several metrics, including Hit@k, Mean Rank (MR), and Mean Reciprocal Rank (MRR). These results validate the effectiveness and potential applications of this method in the domain of link prediction for electrical equipment knowledge graphs.

ScGraphformer: unveiling cellular heterogeneity and interactions in scRNA-seq data using a scalable graph transformer network

The precise classification of cell types from single-cell RNA sequencing (scRNA-seq) data is pivotal for dissecting cellular heterogeneity in biological research. Traditional graph neural network (GNN) models are constrained by reliance on predefined graphs, limiting the exploration of complex cell-to-cell relationships. We introduce scGraphformer, a transformer-based GNN that transcends these limitations by learning an all-encompassing cell-cell relational network directly from scRNA-seq data. Through an iterative refinement process, scGraphformer constructs a dense graph structure that captures the full spectrum of cellular interactions. This comprehensive approach enables the identification of subtle and previously obscured cellular patterns and relationships. Evaluated on multiple datasets, scGraphformer demonstrates superior performance in cell type identification compared to existing methods and showcases its scalability with large-scale datasets. Our method not only provides enhanced cell type classification ability but also reveals the underlying cell interactions, offering deeper insights into functional cellular relationships. The scGraphformer thus holds the potential to significantly advance the field of single-cell analysis and contribute to a more nuanced understanding of cellular behavior.

TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting.

Traffic flow forecasting is crucial for improving urban traffic management and reducing resource consumption. Accurate traffic conditions prediction requires capturing the complex spatial-temporal dependencies inherent in traffic data. Traditional spatial-temporal graph modeling methods often rely on fixed road network structures, failing to account for the dynamic spatial correlations that vary over time. To address this, we propose a Transformer-Enhanced Adaptive Graph Convolutional Network (TEA-GCN) that alternately learns temporal and spatial correlations in traffic data layer-by-layer. Specifically, we design an adaptive graph convolutional module to dynamically capture implicit road dependencies at different time levels and a local-global temporal attention module to simultaneously capture long-term and short-term temporal dependencies. Experimental results on two public traffic datasets demonstrate the effectiveness of the proposed model compared to other state-of-the-art traffic flow prediction methods.

Hierarchical clustering algorithm based on Crystallized neighborhood graph for identifying complex structured datasets

In data mining, the neighborhood graph is an important method for describing the distribution of datasets. However, existing neighborhood graph methods are often sensitive to parameters settings and the presence of outliers. These traditional neighborhood graphs typically necessitate one or more input parameters, and they may not function optimally when applied to complex datasets that include a substantial number of noise points. To overcome these drawbacks, we have received inspiration from crude salt purification, and propose a non-parameter neighborhood graph method named the Crystallized neighborhood graph (CNG). This method can adaptively capture the distribution structure of complex structured datasets. Based on the CNG, we propose a Hierarchical clustering algorithm based on the Crystallized neighborhood graph for identifying complex structured datasets (HCCNG). It redefines the similarity between sub-graphs using the bridges between sub-graphs and the shortest distance between them. Then, sub-graphs are repeatedly merged according to their similarity until the ideal clustering result is achieved. The experimental results show that the HCCNG algorithm can identify not only popular clusters, but also variable-density spherical clusters. Moreover, it performs well on complex structured datasets with a significant amount of noise.

Semi-supervised multi-view feature selection with adaptive similarity fusion and learning

Existing multi-view semi-supervised feature selection methods typically need to calculate the inversion of high-order dense matrices, rendering them impractical for large-scale applications. Meanwhile, traditional works construct similarity graphs on different views and directly fuse these graphs from the view level, ignoring the differences among samples in various views and the interplay between graph learning and feature selection. Consequently, both the reliability of graphs and the discrimination of selected features are compromised. To address these issues, we propose a novel multi-view semi-supervised feature selection with Adaptive Similarity Fusion and Learning (ASFL) for large-scale tasks. Specifically, ASFL constructs bipartite graphs for each view and then leverages the relationships between samples and anchors to align anchors and graphs across different views, preserving the complementarity and consistency among views. Moreover, an effective view-to-sample fusion manner is designed to coalesce the aligned graphs while simultaneously exploiting the neighbor structures in projection subspaces to construct the joint graph compatible across views, reducing the adverse effects of noisy features and outliers. By incorporating bipartite graph fusion and learning, label propagation, and l2,0-norm multi-view feature selection into a unified framework, ASFL not only avoids the expensive computation in the solution procedures but also enhances the quality of selected features. An effective optimization strategy with fast convergence is developed to solve the objective function, and experimental results validate its efficiency and effectiveness over state-of-the-art methods.

Heterogeneous graph neural network for modeling intelligent manufacturing systems

Abstract Currently, manufacturing systems have become more and more complex, often involving multiple machines, systems and processes to produce workpieces. In order to facilitate comprehensive analysis and control of manufacturing processes, the integration of connections between machine level, system level, and process level in manufacturing process modeling is needed. However, traditional graph deep learning models are unable to take into account the heterogeneity of different machines in the system when modeling manufacturing systems. To address this problem, this paper proposes a new approach: modeling manufacturing systems using the heterogeneous graph neural network sample and aggregate algorithm based on cutting-edge Bayesian neural networks and graph deep learning. This method considers the connection between different manufacturing system levels, treats machine operations as nodes, and connects different nodes through material flow and operational similarity. The effectiveness of the method is demonstrated through its application to model an aero-engine blade production line. Extensive numerical experiments show that the proposed graph modeling method is effective in expressing the heterogeneity of different machines and multi-level manufacturing processes. By integrating machine heterogeneity into the modeling of a manufacturing system, it not only facilitates comprehensive analysis and control of the manufacturing process, but also lays the foundation for cost savings and productivity improvements in the manufacturing system.

MGHCN: Multi-graph structures and hypergraph convolutional networks for traffic flow prediction

Accurate and timely traffic flow predictions are essential for effective traffic management and congestion reduction. However, most traditional prediction methods often fail to capture the complex dynamics and correlations within traffic flows due to insufficient processing of spatiotemporal data. Specifically, these methods struggle to integrate and analyze the multi-layered spatial and temporal interactions inherent in traffic data, leading to suboptimal prediction accuracy and robustness. To address this limitation, this paper presents a Multi-Graph Structures and Hypergraph Convolutional Network (MGHCN) that combines diverse graphs and hypergraphs. The MGHCN simplifies the predictive framework by integrating key components that improve its robustness and accuracy. One of the most critical components is the dual hypergraph structure, which captures edge correlations by converting traditional graph edges into hypergraph nodes. To better capture the spatiotemporal correlation of traffic data, a Graph Convolutional Network (GCN) is employed to analyze these hypergraphs in depth. Finally, a novel adjacency matrix and a dynamic graph module are used to accurately simulate interactions between spatiotemporal features, thereby enhancing the accuracy and robustness of predictions. Experimental validation on four distinct real-world traffic datasets shows that MGHCN outperforms existing state-of-the-art traffic prediction methods.

Research on the Construction Method of Curriculum Teaching Knowledge Graph Based on Bi-LSTM and CNN Algorithm

The aim of the paper is to explore a method of constructing a curriculum teaching knowledge graph by combining Bi-LSTM and convolutional neural network (CNN) algorithm. The field of education is constantly seeking innovation to improve teaching results and student learning experience. Knowledge graph, as an advanced technology of structured representation of knowledge, is expected to provide effective support for teaching management and personalized learning. First, this paper introduces the background and significance of the curriculum teaching knowledge graph. By establishing knowledge maps, we can more clearly present the knowledge system and correlation in the curriculum, which helps teachers to design more targeted teaching content and provide personalized learning paths for students. However, traditional knowledge graph construction methods are often faced with problems such as incomplete information capture and inaccurate semantic association, so it is necessary to introduce advanced deep learning algorithms to improve the quality of knowledge graph. Secondly, this paper elaborates on the construction method of fusion Bi-LSTM and CNN algorithm. Bi-LSTM, as a recurrent neural network capable of capturing sequence information, can better model the evolution process of knowledge in the course. As a CNN is good at extracting local features, CNN can effectively capture the spatial structure information in the knowledge graph. By integrating two, we can improve the expression ability and reasoning accuracy of knowledge graph. Further, the experimental results show that the fusion Bi-LSTM and the CNN algorithm have significantly improved the accuracy of information capture and inference compared with the traditional method. In summary, this paper proposes an innovative construction method of curriculum teaching knowledge graph by integrating Bi-LSTM and CNN algorithm, which provides new ideas and solutions for informatization and personalized teaching in the field of education. In the future, the applicability of this method in different disciplines and teaching scenarios can be further discussed, and more advanced technologies can be combined to continuously improve and expand the research.

Enhanced tensor based embedding anchor learning for multi-view clustering

Existing anchor graph based multi-view clustering methods can overcome the problem of high computational cost in traditional multi-view clustering methods. However, the anchor points selected from high-dimensional data often contain irrelevant noise and outliers, which would affect the clustering performance. To address this issue, we propose an embedding anchor based multi-view clustering method, called enhanced tensor based embedding anchor learning (ETEAL). Specifically, we unify the learning process of latent embedding space, anchor points, and anchor graphs into a common framework, which eliminates noise and redundant data in the original space and enhances the synergistic optimization between the components. Meanwhile, we employ an enhanced tensor strategy to constrain the embedding anchor graphs, which exploits the higher-order relationships between views and recovers the global low-rank property of the embedding anchor graphs. Finally, we develop an anchor graph fusion strategy, which significantly reduces the huge overhead of traditional graph fusion that requires the construction of complete graphs. Experimental results on eight benchmark datasets show that the proposed method significantly outperforms other state-of-the-art methods in terms of scalability and clustering accuracy.

Multiconstraint quality–probability graph for quality monitoring of laser directed energy deposition manufacturing process

Quality monitoring of the laser directed energy deposition (LDED) manufacturing process by machine vision is essential to improve the reliability and economy of the LDED manufactured parts. For monitoring algorithms, graph-based semi-supervised learning can effectively learn supervised information from labelled data without the requirement of large amounts of manually labelled data. However, traditional graph algorithm for LDED quality monitoring is limited by insufficient use of label supervised information, inadequate consideration of the imbalance data, and lack of physically meaningful explanations and constraints on the propagation process for different types of defects. In this regard, a multiconstraint quality–probability graph (MCQPG) is proposed to monitor the quality during the LDED manufacturing process. MCQPG converts the extracted multifeatures into probability distributions, finds feature sets with similar distributions to the supervised information based on quality level standards, and uses multiconstraints to satisfy few labelled feature data, imbalance data distribution and physical consistency. For physical consistency, a nonlinear defect model is developed for crack and porosity defects, and a novel defect-guided objective prediction function is proposed, resulting in the construction of a quality level standard guided physical consistency constraint term. Experimental studies on several well-known and commonly used monitoring algorithms demonstrate that the proposed MCQPG algorithm achieves 0.96 on all four evaluation metrics (accuracy, precision, recall and F1 score), validating the effectiveness of MCQPG for LDED quality monitoring.

A Method for Constructing an Urban Waterlogging Emergency Knowledge Graph Based on Spatiotemporal Processes

Urban waterlogging is one of the major “diseases” faced by cities, posing a great challenge to the healthy and sustainable development of cities. The traditional geographic knowledge graph struggles to capture dynamic changes in urban waterlogging over time. Therefore, the objective of this study is to analyze the time, events, properties, geographic objects, and activities associated with urban waterlogging emergency responses from the geographic spatial and temporal processes perspective and to construct an urban waterlogging emergency knowledge graph by combining top-down and bottom-up approaches. We propose a conceptual model of urban waterlogging emergency response ontology based on spatiotemporal processes by analyzing the basic laws and influencing factors of urban waterlogging occurrence and development. Secondly, we describe the construction process of the urban waterlogging emergency response knowledge graph from knowledge extraction, knowledge fusion, and knowledge storage. Finally, the knowledge graph was visualized using 159 urban waterlogging events in China from 2020–2022, with a quality assessment indicating 81% correctness, 65.5% completeness, and 95% data conciseness. The results show that this method can effectively express the spatiotemporal process of an urban waterlogging emergency response and can provide a reference for the spatiotemporal modeling of the knowledge graph.

Optimization of the age of correlated information in V2X networks with edge computing

Vehicle-to-Everything (V2X) communication has the potential to revolutionize the travel experience in intelligent transportation, which has received the great attention recently. However, ensuring the freshness of information from multiple sources is critical for the real-time and reliable communication in vehicular networks, especially for timely updates of service centers. To address this issue, we use a promising metric called Age of Correlated Information (AoCI), which can characterize the freshness of multi-source information. Therefore, we propose a novel model that can dynamically regulate the channel activation matching and edge computing collaboration strategy to minimize AoCI in V2X vehicular networks. Firstly, we describe the system model of a V2X network with edge computing, including definitions and assumptions for freshness of information, edge co-computing, etc. Secondly, we formulate the joint optimization problem as a source-related age minimization (SRAM) problem, which is NP-complete. A heuristic algorithm is proposed to solve it under fast-fading channel. Finally, since traditional graph models cannot capture the changing correlation between nodes in dynamic networks, we use graph convolutional networks(GCN) to extract the features of multi-source correlation. The features extracted by GCN include relevant attributes of the sources and its communication links. The features are provided as input to a double deep Q network (DDQN) for training the model that can adapt to a dynamic network environment. Extensive simulation experiments in different network scenarios validate that our proposed method can effectively and efficiently reduce the average AoCI and the computational resources.

QDN: A Quadruplet Distributor Network for Temporal Knowledge Graph Completion.

Temporal knowledge graph completion (TKGC) is an extension of the traditional static knowledge graph completion (SKGC) by introducing the timestamp. The existing TKGC methods generally translate the original quadruplet to the form of the triplet by integrating the timestamp into the entity/relation, and then use SKGC methods to infer the missing item. However, such an integrating operation largely limits the expressive ability of temporal information and ignores the semantic loss problem due to the fact that entities, relations, and timestamps are located in different spaces. In this article, we propose a novel TKGC method called the quadruplet distributor network (QDN), which independently models the embeddings of entities, relations, and timestamps in their specific spaces to fully capture the semantics and builds the QD to facilitate the information aggregation and distribution among them. Furthermore, the interaction among entities, relations, and timestamps is integrated using a novel quadruplet-specific decoder, which stretches the third-order tensor to the fourth-order to satisfy the TKGC criterion. Equally important, we design a novel temporal regularization that imposes a smoothness constraint on temporal embeddings. Experimental results show that the proposed method outperforms the existing state-of-the-art TKGC methods. The source codes of this article are available at https://github.com/QDN for Temporal Knowledge Graph Completion.git.