Graph Structure Research Articles

A Research Approach to Port Information Security Link Prediction Based on HWA Algorithm

For the protection of information security, link prediction, as a basic problem of network science, has important application significance. However, most of the existing link prediction algorithms rely on the node information of the graph structure, which is not applicable in some graph structure data involving privacy. At the same time, most of the algorithms only consider the general graph structure and do not fully consider the high-order information in the graph. Because of this, this paper proposes an algorithm called hypergraph-based link prediction with self-attention (HWA) to solve the above problems. The algorithm can obtain hypergraphs without knowing the attribute information of hypergraph nodes and combines the graph convolutional network (GCN) framework to capture node feature information for link prediction. Experiments show that the HWA algorithm proposed in this paper, combined with the GCN framework, shows better link prediction performance than other graph-based neural network benchmark algorithms on eight real networks. This further verifies the validity and reliability of the model in this paper and provides new protection ideas and technical means for information security.

Exploring & exploiting high-order graph structure for sparse knowledge graph completion

Exploring & exploiting high-order graph structure for sparse knowledge graph completion

Traffic Flow Prediction Using Novel Spatial-Temporal Multi-Head Attention Graph Convolution Networks

For urban development, accurate traffic flow prediction is crucial. Traffic flow prediction data can be used for optimizing public transportation systems, reducing congestion, planning road networks, and improving overall city infrastructure management. Despite numerous spatiotemporal methods used to forecast traffic flow, information aggregation at each site neither produce optimal results, because of the use non-Euclidean distance data. For more accurate results of traffic flow prediction, we propose a spatial-temporal multi-head attention graph convolution network (STMAGCN). It extracts temporal features using temporal convolutional layers and enriches nodes with spatial attention and multi-head attention mechanisms. By combining them, we can extract space characteristics more effectively. We also introduce a novel graph structure construction method that employs graph-based transformations to convert non-connected data points into a comprehensive graph structure, facilitating the effective application of our STMAGCN. This approach improves the predictive efficiency and accuracy of our model by ensuring seamless integration of disparate data sources. Experimental results indicate that the preferential extraction of spatiotemporal data significantly enhances traffic flow prediction accuracy. Compared with the latest models, our performance on the California Department of Transportation Performance Measurement System (PeMS) PeMS04 and PeMS08 datasets shows a slight improvement, with an average increase of 16.8%. Additionally, the average improvement in time is approximately 445.95%.

Hybrid convolutional network with enhanced graph attention mechanism (HCN-EGAM) for hyperspectral image classification

ABSTRACT Due to their reliance on superficial spectral or spatial information, current hyperspectral image classification techniques frequently fail to generate similarity measures that are accurate enough to create graph structures. We have developed a new end-to-end model, the hybrid convolutional network with enhanced graph attention mechanism (HCN-EGAM), to address this issue. It integrates an enhanced graph attention mechanism with 3D–2D hybrid convolution. In order to improve classification accuracy, this model synergistically uses the graph attention network module with the hybrid convolutional feature extraction module. The model starts by creating a 3D–2D hybrid convolutional network. This lets it quickly pull out deep spatial-spectral features that make different ground objects stand out in hyperspectral images. The model then employs these deep spatial-spectral properties to construct a graph structure, thereby enhancing its feature representation capabilities. Lastly, we use the Enhanced Graph Attention Mechanism (EGAM) to learn long-range spatial associations, successfully distinguishing between intra-class differences and inter-class similarities between distinct samples. Comparing our suggested method to other state-of-the-art methods, experimental assessments on three datasets, including the University of Pavia, Kennedy Space Center (KSC) and Indian Pines (IP) datasets, show a considerable improvement in classification accuracy.

Dynamic graph structure and spatio-temporal representations in wind power forecasting

Wind Power Forecasting (WPF) has gained considerable focus as a crucial aspect of the successful integration and operation of wind power. However, due to the stochastic and unstable nature of wind, it poses a real challenge to effectively analyze the correlations among multiple time series data for accurate prediction. In our study, an end-to-end framework called Dynamic Graph structure and Spatio-Temporal representation learning (DSTG) framework is proposed to achieve stable power forecasting by constructing graph data to capture the critical features in the data. Specifically, a graph structure learning (GSL) module is introduced to dynamically construct task-related correlation matrices via backpropagation to mitigate the inherent inconsistency and randomness of wind power data. Additionally, a dual-scale temporal graph learning (DTG) module is further proposed to explore the implicit spatio-temporal features at a fine-grained level using different skip connections from the constructed graph data. Finally, comprehensive experiments are performed on the collected Xuji Group Wind Power (XGWP) dataset, and the results show that DSTG outperforms the state-of-the-art spatio-temporal methods by 10.12% on the average of root mean square error and mean absolute error, demonstrating the effectiveness of DSTG. In conclusion, our model provides a promising approach.

RGISQL: Integrating Refined Grammatical Information into Relational Graph Neural Network for Text-to-SQL Task

The text-to-SQL task aims to convert natural language questions into corresponding SQL queries based on a given database schema. Previous models that rely on graph neural networks often struggle to accurately capture the complex grammatical relationships present in these questions, leading to poor performance when generating queries for longer requests. To address these challenges, we propose RGISQL, which integrates refined grammatical information extracted from the question and employs segmentation processing to effectively manage long queries. Additionally, RGISQL minimizes the complexity of edge embeddings by reducing the coupling within graph neural networks. By utilizing grammatical dependency trees, RGISQL is better equipped to capture the inherent structure and grammatical rules of questions. This refined grammatical information offers additional contextual and semantic cues for the model, thereby enhancing both its generalizability and interpretability. Furthermore, we dynamically assess the importance of different edges based on the graph structure, which helps reduce the coupling of edge embeddings and further improves the model’s performance. Multiple sets of experiments conducted on the Spider and Spider-Syn datasets demonstrate that RGISQL outperforms other baselines, achieving the best results in both datasets.

Almost exact recovery in noisy semi-supervised learning

Abstract Graph-based semi-supervised learning methods combine the graph structure and labeled data to classify unlabeled data. In this work, we study the effect of a noisy oracle on classification. In particular, we derive the maximum a posteriori (MAP) estimator for clustering a degree corrected stochastic block model when a noisy oracle reveals a fraction of the labels. We then propose an algorithm derived from a continuous relaxation of the MAP, and we establish its consistency. Numerical experiments show that our approach achieves promising performance on synthetic and real data sets, even in the case of very noisy labeled data.

Predicting Ride-Hailing Demand with Consideration of Social Equity: A Case Study of Chengdu

In the realm of shared autonomous vehicle ride-sharing, precise demand prediction is vital for optimizing resource allocation, improving travel efficiency, and promoting sustainable transport solutions. However, existing studies tend to overlook social attributes and demographic characteristics across various regions, resulting in disparities in prediction fairness between areas with plentiful and limited transportation resources. In order to achieve more accurate and fair prediction, an innovative Social Graph Convolution Long Short-Term Memory framework is proposed, incorporating demographic, spatial, and transportation accessibility information into multiple functional graphs, including functional similarity, population structure, and historical demand graphs. Furthermore, Mean Percentage Error indicators are employed in the loss function to balance prediction accuracy and fairness. The findings indicate that there is an enhancement in both prediction accuracy and fairness by at least 8.9% and 12.9%, respectively, compared to base models. Additionally, the predictions for rush hours in both privileged and underprivileged regions exhibit greater precision and rationality, supporting sustainable transport practices. The proposed framework effectively captures the demands of diverse social groups, thereby contributing to the advancement of social equity and long-term sustainability in urban mobility.

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.

Generating Ontology-Learning Training-Data through Verbalization

Ontologies play an important role in the organization and representation of knowledge. However, in most cases, ontologies do not fully cover domain knowledge, resulting in a gap. This gap, often expressed as a lack of concepts, relations, or axioms, is usually filled by domain experts in a manual and tedious process. Utilizing large language models (LLMs) can ease this process; a fine-tuned LLM could receive as input up-to-date and reliable domain knowledge natural text and output a structured graph in OWL RDF/Turtle format, which is the standard format of ontologies. Thus, to fine-tune a model, text-owl sentence pairs that constitute such a dataset must be acquired. Unfortunately, such a dataset does not exist in the literature or within the open-source community. Therefore, this paper introduces our LLM-assisted verbalizer to create such a data set by converting OWL statements from existing ontologies into natural text. We evaluate the verbalizer on 322 classes from four different ontologies using two different LLMs, achieving precision and recall as high as 0.99 and 0.96, respectively.

Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction

Structure-based machine learning algorithms have been utilized to predict the properties of protein-protein interaction (PPI) complexes, such as binding affinity, which is critical for understanding biological mechanisms and disease treatments. While most existing algorithms represent PPI complex graph structures at the atom-scale or residue-scale, these representations can be computationally expensive or may not sufficiently integrate finer chemical-plausible interaction details for improving predictions. Here, we introduce MCGLPPI, a geometric representation learning framework that combines graph neural networks (GNNs) with MARTINI molecular coarse-grained (CG) models to predict PPI overall properties accurately and efficiently. Extensive experiments on three types of downstream PPI property prediction tasks demonstrate that at the CG-scale, MCGLPPI achieves competitive performance compared with the counterparts at the atom- and residue-scale, but with only a third of computational resource consumption. Furthermore, CG-scale pre-training on protein domain-domain interaction structures enhances its predictive capabilities for PPI tasks. MCGLPPI offers an effective and efficient solution for PPI overall property predictions, serving as a promising tool for the large-scale analysis of biomolecular interactions.

Subthalamic nucleus deep brain stimulation modulates speech graphs in patients with Parkinson’s disease

Graph theory enables a direct quantification of topological properties of any arbitrary network. Its application in neuroscience has unveiled topological changes of brain networks associated with various neurodegenerative diseases. This study used the graph theory to understand speech deficits in patients with Parkinson’s disease (PD). In particular, this study investigated the effect of subthalamic nucleus deep brain stimulation (STN-DBS) on the topology of speech graphs. Sixty patients with PD completed a standard semantic fluency test with DBS switched ON and OFF. A control group of sixty matched nonsurgical PD patients completed the test once. All verbal responses were recorded, transcripted, and transformed into directed speech graphs. Volumes of tissue activated (VTA) were estimated for three STN subregions, including sensorimotor, associative, and limbic parts. First, the patients with DBS OFF produced smaller and denser speech graphs than nonsurgical patients, showing fewer nodes, higher density, shorter diameter, and shorter average shortest path. Second, DBS partially reversed the effect of surgery, leading to larger and sparser speech graphs with more nodes, lower density, longer diameter, and longer average shortest path (ON versus OFF). Third, however, the left associative VTA negatively correlated with the DBS-induced diameter and average shortest path changes (ON versus OFF), suggesting that the patients with greater left associative STN stimulation tended to produce smaller and denser speech graphs. This study demonstrates that STN-DBS can partially restore the topological structure of speech graphs in PD patients. However, stimulating the left associative STN appears to disrupt speech graphs.

Accelerating graph-based tracking tasks with symbolic regression

Abstract The reconstruction of particle tracks from hits in tracking detectors is a computationally intensive task due to the large combinatorics of detector signals. Recent efforts have proven that ML techniques can be successfully applied to the tracking problem, extending and improving the conventional methods based on feature engineering. 
However, complex models can be challenging to implement on heterogeneous trigger systems, integrating architectures such as FPGAs.
Deploying the network on an FPGA is feasible but challenging and limited by its resources. An efficient alternative can employ symbolic regression (SR). We propose a novel approach that uses SR to replace a graph-based neural network. Substituting each network block with a symbolic function preserves the graph structure of the data and enables message passing. 
The technique is perfectly suitable for heterogeneous hardware, as it can be implemented more easily on FPGAs and grants faster execution times on CPU with respect to conventional methods.
While the tracking problem is the target for this work, it also provides a proof-of-principle for the method that can be applied to many use cases.

Intricate Supply Chain Demand Forecasting Based on Graph Convolution Network

Globalization has contributed to the increasing complexity of supply chain structures. In this regard, precise demand forecasting for the intricate supply chain holds paramount importance in effective supply chain management. Traditional statistical models and deep learning methods often face challenges in efficiently discerning correlations within a myriad of interconnected demands. To tackle this issue, this paper proposes an intricate supply chain demand forecasting method based on graph convolution networks adept at handling non-Euclidean data. First, the companies within the supply chain are treated as nodes in the graph structure, and the relationships between them are treated as edges, with demand data serving as the features of these edges. Then, a graph convolutional network is constructed to aggregate node and edge information. Through a multi-layer network, the relationships among nodes, edges, and historical demand are established to facilitate the prediction of supply chain demands. In this process, the graph convolutional network incorporates supply chain connectivity information into demand time series analysis. This integration of surface-level topological features and deeper latent correlation attributes across the supply chain’s nodes refines the demand forecasting precision across the entire supply chain. The validation experiment in this paper is grounded in sales data of a singular product from multiple sales nodes of an electronics company. The results demonstrate that the proposed method surpasses four other traditional demand forecasting algorithms significantly in terms of accuracy, providing substantial evidence for the superior performance of graph networks in the analysis of intricate supply chain relationships.

Flexible Krylov methods for group sparsity regularization

Abstract This paper introduces new solvers for efficiently computing solutions to large-scale inverse problems with group sparsity regularization, including both non-overlapping and overlapping groups. Group sparsity regularization refers to a type of structured sparsity regularization, where the goal is to impose additional structure in the regularization process by assigning variables to predefined groups that may represent graph or network structures. Special cases of group sparsity regularization include ℓ 1 and isotropic total variation regularization. In this work, we develop hybrid projection methods based on flexible Krylov subspaces, where we first recast the group sparsity regularization term as a sequence of 2-norm penalization terms using adaptive regularization matrices in an iterative reweighted norm fashion. Then we exploit flexible preconditioning techniques to efficiently incorporate the weight updates. The main advantages of these methods are that they are computationally efficient (leveraging the advantages of flexible methods), they are general (and therefore very easily adaptable to new regularization term choices), and they are able to select the regularization parameters automatically and adaptively (exploiting the advantages of hybrid methods). Extensions to multiple regularization terms and solution decomposition frameworks (e.g. for anomaly detection) are described, and a variety of numerical examples demonstrate both the efficiency and accuracy of the proposed approaches compared to existing solvers.

Multi-view graph contrastive representation learning for bundle recommendation

Bundle recommendation can recommend a collection of associated items that can be consumed together to a user rather than recommending these items separately, making it extremely suitable for some scenarios such as product bundle recommendation and game bundle recommendation. Recent bundle recommendation approaches consider auxiliary data to mitigate sparse user-bundle interactions. However, these approaches obtain the node embeddings directly from the established user-bundle graph and do not explicitly exploit the relationships between users (bundles) when constructing recommendation models. Moreover, bundle recommendation approaches based on graph contrastive learning usually construct contrastive views by randomly discarding nodes (edges) in the graph, while discarding some essential nodes or edges will destroy the structure of the original graph, thereby deteriorating the quality of the learned node embeddings. Aiming at these limitations, we propose a bundle recommendation approach based on multi-view graph contrastive representation learning. First, we present a multi-view modeling method to model the relations between entities as several views from different perspectives. These views serve as inputs of graph neural networks for graph representation learning and provide contrastive views for the contrastive learning tasks. Second, we propose a novel framework for bundle recommendation. This framework obtains the user (bundle) embeddings from different views by performing multi-view graph representation learning and enhances the learned user and bundle embeddings through a two-level contrastive learning strategy. On this basis, the enhanced user (bundle) embeddings are fused for prediction. Finally, we design a joint optimization objective to optimize the model parameters, combining the prediction loss that supports multiple negative samples and the contrastive losses. Experiments on the Netease and Youshu datasets reveal that our approach outperforms the state-of-the-art (SOTA) baselines. Furthermore, the average improvements of Recall@K and NDCG@K of our approach over the SOTA baselines are approximately 3.38% and 2.80% on Netease and 3.94% and 4.84% on Youshu.

Making It Tractable to Detect and Correct Errors in Graphs

This paper develops \(\mathsf {Hercules} \) , a system for entity resolution (ER), conflict resolution (CR), timeliness deduction (TD) and missing value/link imputation (MI) in graphs. It proposes \(\mathsf {GCR^{+}\!s} \) , a class of graph cleaning rules that support not only predicates for ER and CR, but also temporal orders to deduce timeliness and data extraction to impute missing data. As opposed to previous graph rules, \(\mathsf {GCR^{+}\!s} \) are defined with a dual graph pattern to accommodate irregular structures of schemaless graphs, and adopt patterns of a star form to reduce the complexity. We show that while the implication and satisfiability problems are intractable for \(\mathsf {GCR^{+}\!s} \) , it is in PTIME to detect and correct errors with \(\mathsf {GCR^{+}\!s} \) . Underlying \(\mathsf {Hercules} \) , we train a ranking model to predict the temporal orders on attributes, and embed it as a predicate of \(\mathsf {GCR^{+}\!s} \) . We provide an algorithm for discovering \(\mathsf {GCR^{+}\!s} \) by combining the generations of patterns and predicates. We also develop a method for conducting ER, CR, TD and MI in the same process to improve the overall quality of graphs, by leveraging their interactions and chasing with \(\mathsf {GCR^{+}\!s} \) ; we show that the method has the Church-Rosser property under certain conditions. Using real-life and synthetic graphs, we empirically verify that \(\mathsf {Hercules} \) is 53% more accurate than the state-of-the-art graph cleaning systems, and performs comparably in efficiency and scalability.

Unraveling the impact of mutations on the functional dynamics, stability, and energetics of dengue virus non-structural protein 1

ABSTRACT The non-structural protein 1 (NS1), a viral toxin, is linked to serious consequences of dengue. Given its crucial role in the viral life cycle, NS1 has been a primary target for antiviral drug development. This study elucidates the mechanistic impact of specific NS1 mutations, V220D and A248V, identified by Tan and colleagues as potential inhibitors of viral replication. We developed an integrated computational framework to analyze these mutations relative to the native NS1 protein. Using conventional all-atom molecular dynamic simulations followed by site-directed in silico mutagenesis, significant alterations in protein structure were observed. Conformational ensembles over time showed average backbone deviations of 0.44 nm and 0.43 nm for V220D and A248V, respectively, compared to 0.37 nm for the wild type. Residue-wise fluctuations were higher in A248V compared to both wild type and V220D systems. Mutation-induced disruptions in the hydrogen bond network and altered protein structure graphs were also revealed. Principal component analysis and free energy landscape assessments showed the wild-type protein had a more constrained and stable conformation, whereas the mutants displayed scattered energy contours, suggesting reduced structural stability. This comprehensive assessment provides deep insight into the structural impact of NS1 mutations, informing future efforts in antiviral drug development targeting NS1.

Leveraging Knowledge Graphs for Enhanced Medical Reasoning in Personalized Medicine for Rare Diseases

Leveraging knowledge graphs offers a promising approach to enhancing medical reasoning in the personalized treatment of rare diseases. Knowledge graphs provide an effective framework for organizing and interpreting complex biomedical data, facilitating a more comprehensive approach to diagnosis, prognosis, and treatment of rare diseases. By integrating diverse data sources—such as genomic profiles, clinical histories, and pharmacological information—into a cohesive graph structure, the project aims to improve clinical outcomes by enabling patient-specific insights and treatment recommendations. Rare diseases pose unique challenges due to limited data and complex symptoms, making traditional diagnostic methods inadequate. Knowledge graphs have the potential to bridge these gaps by linking disparate datasets, allowing clinicians to identify biomarkers, make more accurate diagnoses, and formulate personalized treatment pathways. This project involves constructing a multi-layered knowledge graph, applying machine learning and reasoning algorithms for pattern detection, and validating its accuracy in real-world settings. Expected outcomes include improved diagnostic accuracy, the discovery of new biomarkers, and the development of a scalable knowledge graph framework adaptable for a wide range of diseases. This work aims to contribute to the advancement of personalized medicine, offering a model for AI-driven reasoning that supports more informed and timely clinical decisions in the treatment of rare diseases. By organizing complex biomedical data into interconnected graphs, clinicians can gain comprehensive insights into rare disease mechanisms, facilitating more accurate diagnoses and personalized treatment strategies. Integrating diverse data sources, such as genomic, clinical, and pharmacological information, the knowledge graph structure enables the identification of relationships and patterns that are often missed in traditional analyses. Machine learning algorithms further support this process by identifying potential biomarkers and recommending treatment pathways based on patient-specific data. Through real-world validation with clinical partners, the knowledge graph approach is expected to improve diagnostic accuracy and support early intervention strategies. Ultimately, this framework not only addresses the unique challenges of treating rare diseases but also establishes a scalable model that can be adapted for broader applications in personalized medicine.

GACT-PPIS: Prediction of protein-protein interaction sites based on graph structure and transformer network

The prediction of protein-protein interaction sites (PPIS) is currently crucial for regulating many biological activities in cells and developing drugs for various diseases. Deep learning-based methods have been proposed for predicting PPIS, significantly reducing the manpower and time costs associated with traditional experimental methods such as yeast two-hybrid, mass spectrometry, and affinity purification. However, the predictive accuracy of these deep learning methods has not yet reached the expected level. Therefore, we introduce a model called GACT-PPIS.The design of the GACT-PPIS algorithm aims to utilize combined information from protein sequences and structures as input to predict protein-protein interaction sites. The core of GACT-PPIS utilizes an Enhanced Graph Attention Network (EGAT) with initial residual and identity mappings, along with a deep Transformer network as the basic units, supplemented by Graph Convolutional Networks (GCN), effectively aggregating information from neighboring nodes for each node. After multiple network layers, the information of the entire protein is also fused into the nodes, and the Transformer network further enhances the model's performance.Experimental results show that GACT-PPIS outperforms the most representative models in terms of Recall, F1-measure, MCC, AUROC, and AUPRC on the benchmark test set (Test-60). Additionally, on other independent test sets (UBTest-31-6), GACT-PPIS leads in terms of Accuracy, Precision, Recall, F1-measure, MCC, AUROC, and AUPRC compared to the most representative models. It is worth noting that GACT-PPIS demonstrates excellent generalization and versatility across different test sets, showcasing good performance on multiple test sets for the same trained GACT-PPIS model.