Static Graphs Research Articles

Multi-site solar irradiance prediction based on hybrid spatiotemporal graph neural network

Constructing accurate spatiotemporal correlations is a challenging task in joint prediction of multiple photovoltaic sites. Some advanced algorithms for incorporating other surrounding site information have been proposed, such as graph neural network-based methods, which are usually based on static or dynamic graphs to build spatial dependencies between sites. However, the possibility of the simultaneous existence of multiple spatial dependencies is not considered. This paper establishes a spatiotemporal prediction model based on hybrid spatiotemporal graph neural network. In this model, we apply adaptive hybrid graph learning to learn composite spatial correlations among multiple sites. A temporal convolution module with multi-subsequence temporal data input is used to extract local semantic information to better predict future nonlinear temporal dependencies. A spatiotemporal adaptive fusion module is added to address the issue of integrating diverse spatiotemporal trends among multiple sites. To assess the model's predictive performance, nine solar radiation observation stations were selected in two different climatic environments. The average root mean square error (RMSE) of the constructed model was 38.51 and 49.90 W/m2, with average mean absolute error (MAE) of 14.72 and 23.06 W/m2, respectively. Single-site and multi-site prediction models were selected as baseline models. Compared with the baseline models, the RMSE and MAE reduce by 3.1%–20.8% and 8.9%–32.8%, respectively, across all sites. The proposed model demonstrates the effectiveness of improving accuracy in forecasting solar irradiance through multi-site predictions.

STAD-GCN: Spatial–Temporal Attention-based Dynamic Graph Convolutional Network for retail market price prediction

As technology advances, competition among market players intensifies, highlighting the importance of comprehending both one’s own and competitors’ pricing strategies. Traditional approaches often rely on static factors for price forecasting, disregarding the dynamic nature of market competition. In contrast to methods utilizing a static graph structure and uniform weights for predictions, we introduce STAD-GCN (Spatial–Temporal Attention-based Dynamic Graph Convolutional Network). This innovative model dynamically incorporates competitive factors into price prediction by employing attention mechanisms and graph convolution operations. Such an approach allows for the adaptation of graph structures and node relationships in response to temporal and spatial changes, offering a more nuanced understanding of market dynamics. To test STAD-GCN, we utilized international and domestic oil price data alongside specific gas station details from the South Korea National Oil Corporation, focusing on Seoul and Busan. The model presents remarkable performance, achieving mean absolute errors of 12.648 in Seoul and 11.242 in Busan, surpassing state-of-the-art models. Based on the findings of our research, we present some academic and practical implications, as well as several future research directions.

A deep learning model integrating a wind direction-based dynamic graph network for ozone prediction

Ozone pollution is an important environmental issue in many countries. Accurate forecasting of ozone concentration enables relevant authorities to enact timely policies to mitigate adverse impacts. This study develops a novel hybrid deep learning model, named wind direction-based dynamic spatio-temporal graph network (WDDSTG-Net), for hourly ozone concentration prediction. The model uses a dynamic directed graph structure based on hourly changing wind direction data to capture evolving spatial relationships between air quality monitoring stations. It applied the graph attention mechanism to compute dynamic weights between connected stations, thereby aggregating neighborhood information adaptively. For temporal modeling, it utilized a sequence-to-sequence model with attention mechanism to extract long-range temporal dependencies. Additionally, it integrated meteorological predictions to guide the ozone forecasting. The model achieves a mean absolute error of 6.69 μg/m3 and 18.63 μg/m3 for 1-h prediction and 24-h prediction, outperforming several classic models. The model's IAQI accuracy predictions at all stations are above 75 %, with a maximum of 81.74 %. It also exhibits strong capabilities in predicting severe ozone pollution events, with a 24-h true positive rate of 0.77. Compared to traditional static graph models, WDDSTG-Net demonstrates the importance of incorporating short-term wind fluctuations and transport dynamics for data-driven air quality modeling. In principle, it may serve as an effective data-driven approach for the concentration prediction of other airborne pollutants.

Inter-structure and intra-semantics graph contrastive learning for disease prediction

Ever-evolving healthcare applications have witnessed a surge in the utilization of electronic health records (EHR) for predicting future patient diagnoses. While Graph Neural Networks have demonstrated that promise in modeling disease-patient relationships, challenges arise from the sparsity and imbalance of patient and diagnostic data. Moreover, the existing models face difficulties in learning the unique disease combination features of patients. To address these challenges, we proposed a novel disease. prediction architecture based on Contrastive Learning (CL) from interstructural and intrasemantic perspectives, rather than traditional CL methods. We generated an initial global static disease graph to directly represent the relationships. among all diseases and a local dynamic disease graph to capture the indirect latent disease relationships among different patients. Multiple CL tasks were designed to learn sparse and imbalanced potentials. Relationships Between Diseases. Interstructure graph CL was first proposed to sample a graph enhancement, based on the distribution of nodes in the global disease graph. To further explore the deep embedding space of the disease, an intra-view graph CL was introduced by injecting noise at the semantic level for robust graph comparison. Experimental validation on two real EHR datasets demonstrates the superior performance of the approach by comparing it with state-of-the-art models.

Deep Graph Neural Networks for Malware Detection Using Ghidra P-Code

This work examines the effectiveness of using Ghidra P-Code as semantics-based features in a graph neural network-based malware detection system. A preliminary model exhibits a function level precision of ∼70% and a recall around ∼60%, and a precision and recall of ~55% and ~80% respectively for the program level detection task on a dataset of ∼50,000 control flow graphs extracted from functions of malicious and benign programs. Future improvements to this ongoing project include, but are not limited to, collecting dynamic control flow graph information as opposed to static graphs to provide the model with resilience to advanced malware obfuscation and encryption schemes.

Self-supervised dynamic stochastic graph network for spatio-temporal wind speed forecasting

Spatio-temporal Forecasting has been implemented in diverse fields, such as energy, traffic, and weather. As one typical paradigm of intelligent power systems, spatio-temporal wind speed forecasting has attracted increasing attention. Recently, some graph-based methods have revealed the great potential in the spatio-temporal wind speed forecasting task. Those methods are usually built on a static graph which is incapable of discovering the dynamic characteristics and the uncertainty of temporal wind patterns. To this end, we propose a novel Dynamic Stochastic Graph Network (DSGN) for spatio-temporal wind speed forecasting. Specifically, we characterize each wind turbine of regional power grids with a dynamic stochastic distribution to incorporate the uncertainty into networks. Then Wasserstein distance is adopted to build the stochastic graph, which can effectively represent the spatial dependencies between wind turbines. Additionally, we devise a reconstruction task to preserve the geographical distribution information and regularize the learning of the stochastic graph. To further exploit global spatial dependencies and enhance graph modeling, we augment the stochastic graph view by diffusion operations and integrate a self-supervised learning framework, serving as an auxiliary task, to maximize mutual information between the wind latent states from different graph views. Empirical experiments on four real-world wind speed datasets demonstrate the superiority of DSGN over some state-of-the-art methods. Some ablation studies further validate the effectiveness of the stochastic graph modeling and the self-supervised framework.

Temporal dynamics unleashed: Elevating variational graph attention

This research introduces the Variational Graph Attention Dynamics (VarGATDyn), addressing the complexities of dynamic graph representation learning, where existing models, tailored for static graphs, prove inadequate. VarGATDyn melds attention mechanisms with a Markovian assumption to surpass the challenges of maintaining temporal consistency and the extensive dataset requirements typical of RNN-based frameworks. It harnesses the strengths of the Variational Graph Auto-Encoder (VGAE) framework, Graph Attention Networks (GAT), and Gaussian Mixture Models (GMM) to adeptly navigate the temporal and structural intricacies of dynamic graphs. Through the strategic application of GMMs, the model handles multimodal patterns, thereby rectifying misalignments between prior and estimated posterior distributions. An innovative multiple-learning methodology bolsters the model’s adaptability, leading to an encompassing and effective learning process. Empirical tests underscore VarGATDyn’s dominance in dynamic link prediction across various datasets, highlighting its proficiency in capturing multimodal distributions and temporal dynamics.

Asymptotic dynamic graph order evolution analysis

In this work, we investigate the analysis of generators for dynamic graphs, which are defined as graphs whose topology changes over time. We focus on generated graphs whose order (number of nodes) varies over time. We use a concept called “sustainability” to qualify the long-term evolution of dynamic graphs. A dynamic graph is considered sustainable if its evolution does not result in a static, empty, or periodic graph. To illustrate how the analysis can be conducted, a parameterized and probability-based generator, named D3G3 (Degree-Driven Dynamic Geometric Graphs Generator), has been introduced in a recent work. From this model, we derive multiple scenarios that correspond to three trends in graph order evolution. Our central contribution lies in a mathematical framework that provides an expectation of the order of the graph at time step t+1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$t+1$$\\end{document}, given its order at time step t. Nevertheless, our analysis underscores the challenge of characterizing the sustainability of dynamic graphs, even when a formal mathematical model for graph order evolution is known.

DeGAN - Decomposition-based unified anomaly detection in static networks

Graph anomaly detection aims to identify anomalous occurrences in networks. However, this is more challenging than the traditional anomaly detection problem because anomalies in graphs can manifest in three different forms: anomalous nodes, anomalous edges, and anomalous sub-graphs. It is crucial to detect all these anomaly types within a single framework to provide a unified solution to the graph anomaly detection task. The main objective of this study is to propose a model that is capable of detecting all static graph anomalies in a single architecture across various domains. In this paper, we introduce DeGAN (Decomposition-based unified Graph ANomaly detection), a novel framework for unified graph anomaly detection in static networks. DeGAN combines two deep learning concepts with graph decomposition to identify anomalous graph objects: a graph neural network and an adversarial autoencoder. DeGAN is featured with its capability to detect anomalies in a single process, and adopting graph decomposition has improved performance compared to the traditional adversarial learning approach. DeGAN is evaluated with six real-world datasets to demonstrate that our framework can work in multiple domains. Experimental results demonstrate that DeGAN is capable of detecting anomalous nodes, edges, and sub-graphs within a single model. Additionally, the effectiveness of the sub-components of DeGAN has been demonstrated through experimentation. Even though DeGAN is proposed for plain graphs, it can be extended to attributed and dynamic graphs.

Improving static and temporal knowledge graph embedding using affine transformations of entities

To find a suitable embedding for a knowledge graph (KG) remains a big challenge nowadays. By measuring the distance or plausibility of triples and quadruples in static and temporal knowledge graphs, many reliable knowledge graph embedding (KGE) models are proposed. However, these classical models may not be able to represent and infer various relation patterns well, such as TransE cannot represent symmetric relations, DistMult cannot represent inverse relations, RotatE cannot represent multiple relations, etc.. In this paper, we improve the ability of these models to represent various relation patterns by introducing the affine transformation framework. Specifically, we first utilize a set of affine transformations related to each relation or timestamp to operate on entity vectors, and then these transformed vectors can be applied not only to static KGE models, but also to temporal KGE models. The main advantage of using affine transformations is their good geometry properties with interpretability. Our experimental results demonstrate that the proposed intuitive design with affine transformations provides a statistically significant increase in performance with adding a few extra processing steps and keeping the same number of embedding parameters. Taking TransE as an example, we employ the scale transformation (the special case of an affine transformation). Surprisingly, it even outperforms RotatE to some extent on various datasets. We also introduce affine transformations into RotatE, Distmult, ComplEx, TTransE and TComplEx respectively, and experiments demonstrate that affine transformations consistently and significantly improve the performance of state-of-the-art KGE models on both static and temporal knowledge graph benchmarks.

A dynamic multigraph and multidimensional attention neural network model for metro passenger flow prediction

SummaryPassenger flow prediction is an important part of daily metro operation, and its accuracy affects the deployment of train resources management. Due to the complex spatiotemporal correlation characteristics of metro passenger flow, it is necessary to describe it to improve the accuracy of passenger flow prediction. However, the existing models mainly construct the weight matrix based on the static graph and the similarity between stations when describing the spatial correlation of station passenger flow but ignore the time‐varying characteristics of the spatial correlation of station passenger flow. To address this problem, this study introduces a dynamic multi‐graph and multidimensional attention spatiotemporal model. Specifically, the Graph Convolutional Neural Network combined with dynamic multigraph extracts spatial features and the Gated Recurrent Unit extracts temporal features of passenger flow. The multidimensional attention can obtain the spatiotemporal correlation of passenger flow data by assigning weights to them. Finally, this model has been used to conduct experiments on Beijing metro passenger flow datasets with time granularity of 10 and 15 min. The result indicates that the DGMANN model outperforms state‐of‐the‐art other deep learning methods in passenger flow prediction. In addition, the effectiveness of its key submodules has been verified through ablation experiments.

Static graph approximations of dynamic contact networks for epidemic forecasting.

Epidemic modeling is essential in understanding the spread of infectious diseases like COVID-19 and devising effective intervention strategies to control them. Recently, network-based disease models have integrated traditional compartment-based modeling with real-world contact graphs and shown promising results. However, in an ongoing epidemic, future contact network patterns are not observed yet. To address this, we use aggregated static networks to approximate future contacts for disease modeling. The standard method in the literature concatenates all edges from a dynamic graph into one collapsed graph, called the full static graph. However, the full static graph often leads to severe overestimation of key epidemic characteristics. Therefore, we propose two novel static network approximation methods, DegMST and EdgeMST, designed to preserve the sparsity of real world contact network while remaining connected. DegMST and EdgeMST use the frequency of temporal edges and the node degrees respectively to preserve sparsity. Our analysis show that our models more closely resemble the network characteristics of the dynamic graph compared to the full static ones. Moreover, our analysis on seven real-world contact networks suggests EdgeMST yield more accurate estimations of disease dynamics for epidemic forecasting when compared to the standard full static method.

TEA+ : A Novel Temporal Graph Random Walk Engine with Hybrid Storage Architecture

Many real-world networks are characterized by being temporal and dynamic, wherein the temporal information signifies the changes in connections, such as the addition or removal of links between nodes. Employing random walks on these temporal networks is a crucial technique for understanding the structural evolution of such graphs over time. However, existing state-of-the-art sampling methods are designed for traditional static graphs, and as such, they struggle to efficiently handle the dynamic aspects of temporal networks. This deficiency can be attributed to several challenges, including increased sampling complexity, extensive index space, limited programmability, and a lack of scalability. In this article, we introduce TEA+ , a robust, fast, and scalable engine for conducting random walks on temporal graphs. Central to TEA+ is an innovative hybrid sampling method that amalgamates two Monte Carlo sampling techniques. This fusion significantly diminishes space complexity while maintaining a fast sampling speed. Additionally, TEA+ integrates a range of optimizations that significantly enhance sampling efficiency. This is further supported by an effective graph updating strategy, skilled in managing dynamic graph modifications and adeptly handling the insertion and deletion of both edges and vertices. For ease of implementation, we propose a temporal-centric programming model, designed to simplify the development of various random walk algorithms on temporal graphs. To ensure optimal performance across storage constraints, TEA+ features a degree-aware hybrid storage architecture, capable of adeptly scaling in different memory environments. Experimental results showcase the prowess of TEA+ , as it attains up to three orders of magnitude speedups compared to current random walk engines on extensive temporal graphs.

A new temporal interpretation of cluster editing

The NP-complete graph problem Cluster Editing seeks to transform a static graph into a disjoint union of cliques by making the fewest possible edits to the edges. We introduce a natural interpretation of this problem in temporal graphs, whose edge sets change over time. This problem is NP-complete even when restricted to temporal graphs whose underlying graph is a path, but we obtain two polynomial-time algorithms for restricted cases. In the static setting, it is well-known that a graph is a disjoint union of cliques if and only if it contains no induced copy of P3; we demonstrate that no general characterisation involving sets of at most four vertices can exist in the temporal setting, but obtain a complete characterisation involving forbidden configurations on at most five vertices. This characterisation gives rise to an FPT algorithm parameterised simultaneously by the permitted number of modifications and the lifetime of the temporal graph.

Backbone-based Dynamic Spatio-Temporal Graph Neural Network for epidemic forecasting

Accurate epidemic forecasting is a critical task in controlling epidemic spread. Many deep learning-based models focus only on static or dynamic graphs when dealing with spatial information, ignoring their relationship. Additionally, these models often rely on recurrent structures, which can lead to error accumulation and computational time consumption. To address the aforementioned problems, we propose a novel model called Backbone-based Dynamic Spatio-Temporal Graph Neural Network (BDSTGNN). Intuitively, the continuous and smooth changes in graph structure make adjacent graph structures share a basic pattern. To capture this property, we use adaptive methods to generate static backbone graphs containing the primary information, and use temporal models to generate dynamic temporal graphs, and then fuse them to generate a backbone-based dynamic graph. To overcome potential limitations associated with recurrent structures, we introduce a linear model DLinear to handle temporal dependencies, and combine it with dynamic graph convolution for epidemic forecasting. Extensive experiments on two datasets demonstrate that BDSTGNN outperforms baseline models, and ablation comparison further verifies the effectiveness of model components. Furthermore, we analyze and measure the significance of backbone and temporal graphs by using information metrics from different aspects. Finally, we verify the superior efficiency of the BDSTGNN.

A recurrent graph neural network for inductive representation learning on dynamic graphs

Graph representation learning has recently garnered significant attention due to its wide applications in graph analysis tasks. It is well-known that real-world networks are dynamic, with edges and nodes evolving over time. This presents unique challenges that are distinct from those of static networks. However, most graph representation learning methods are either designed for static graphs, or address only partial challenges associated with dynamic graphs. They overlook the intricate interplay between topology and temporality in the evolution of dynamic graphs and the complexity of sequence modeling. Therefore, we propose a new dynamic graph representation learning model, called as R-GraphSAGE, which takes comprehensive considerations for embedding dynamic graphs. By incorporating a recurrent structure into GraphSAGE, the proposed R-GraphSAGE explores structural and temporal patterns integrally to capture more fine-grained evolving patterns of dynamic graphs. Additionally, it offers a lightweight architecture to decrease the computational costs for handling snapshot sequences, achieving a balance between performance and complexity. Moreover, it can inductively process the addition of new nodes and adapt to the situations without labels and node attributes. The performance of the proposed R-GraphSAGE is evaluated across various downstream tasks with both synthetic and real-world networks. The experimental results demonstrate that it outperforms state-of-the-art baselines by a significant margin in most cases.

Learning dynamic graph representations through timespan view contrasts

The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node features and topological properties within static graphs to create self-supervised signals, neglecting the temporal components carried by real-world graph data, such as timestamps of edges. To overcome this limitation, this paper explores how to model temporal evolution on dynamic graphs elegantly. Specifically, we introduce a new inductive bias, namely temporal translation invariance, which illustrates the tendency of the identical node to keep similar labels across different timespans. Based on this assumption, we develop a dynamic graph representation framework CLDG that encourages the node to maintain locally consistent temporal translation invariance through contrastive learning on different timespans. Except for standard CLDG which only considers explicit topological links, our further proposed CLDG＋＋additionally employs graph diffusion to uncover global contextual correlations between nodes, and designs a multi-scale contrastive learning objective composed of local–local, local–global, and global–global contrasts to enhance representation capabilities. Interestingly, by measuring the consistency between different timespans to shape anomaly indicators, CLDG and CLDG＋＋are seamlessly integrated with the task of spotting anomalies on dynamic graphs, which has broad applications in many high-impact domains, such as finance, cybersecurity, and healthcare. Experiments demonstrate that CLDG and CLDG＋＋both exhibit desirable performance in downstream tasks including node classification and dynamic graph anomaly detection. Moreover, CLDG significantly reduces time and space complexity by implicitly exploiting temporal cues instead of complicated sequence models. The code and data are available at https://github.com/yimingxu24/CLDG.

WITHDRAWN: FCDNet: Frequency-guided complementary dependency modeling for multivariate time-series forecasting

Multivariate time-series (MTS) forecasting is a challenging task in many real-world non-stationary dynamic scenarios. In addition to intra-series temporal signals, the inter-series dependency also plays a crucial role in shaping future trends. How to enable the model’s awareness of dependency information has raised substantial research attention. Previous approaches have either presupposed dependency constraints based on domain knowledge or imposed them using real-time feature similarity. However, MTS data often exhibit both enduring long-term stable relationships and transient short-term interactions, which mutually influence their evolving states. It is necessary to recognize and incorporate the complementary dependencies for more accurate MTS forecasting. The frequency information in time series reflects the evolutionary rules behind complex temporal dynamics, and different frequency components can be used to well construct interactive dependency structures with varying states between variables. To this end, we propose FCDNet, a concise yet effective complementary dependency modeling framework for multivariate time-series forecasting. Specifically, FCDNet overcomes the above limitations by applying two lightweight dependency constructors to help extract stable static and dynamic varying dependency information adaptively from long short-term multi-level frequency patterns. With the growth of input variables, the number of trainable parameters in FCDNet only increases linearly, which is conducive to the model’s scalability and avoids over-fitting. Additionally, adopting a frequency-based perspective can effectively mitigate the influence of noise within MTS data, which helps capture more genuine dependencies. The experimental results on six real-world datasets from multiple fields show that FCDNet significantly exceeds strong baselines, with an average improvement of 6.82% on MAE, 4.98% on RMSE, and 4.91% on MAPE. In addition, the ability of FCDNet to jointly learn high-quality static and dynamic graph structures is demonstrated empirically. Our source codes are publicly available at https://github.com/onceCWJ/FCDNet.

Revolutionary Strategy for Depicting Knowledge Graphs with Temporal Attributes

In practical applications, the temporal completeness of knowledge graphs is of great importance. However, previous studies have mostly focused on static knowledge graphs, generally neglecting the dynamic evolutionary properties of facts. Moreover, the unpredictable and limited availability of temporal knowledge graphs, together with the complex temporal dependency patterns, make current models inadequate for effectively describing facts that experience temporal transitions. To better represent the evolution of things over time, we provide a learning technique that uses quaternion rotation to describe temporal knowledge graphs. This technique describes the evolution of entities as a temporal rotation change in quaternion space. Compared to the Ermitian inner product in complex number space, the Hamiltonian product in quaternion space is better at showing how things might be connected. This leads to a learning process that is both more effective and more articulate. Experimental results demonstrate that our learning method significantly outperforms existing methods in capturing the dynamic evolution of temporal knowledge graphs, with improved accuracy and robustness across a range of benchmark datasets.

A large-scale graph clustering method for cell conditions spatio-temporal localization in aluminum electrolysis

Sensor nodes (industrial nodes) clustering is an efficacious method for gaining local working conditions real-timely in the production process. The existing deep graph neural networks-based industrial nodes clustering studies construct static graphs to describe the potential spatial correlation among industrial nodes, but the temporal correlation among industrial nodes is ignored, resulting in inferior real-time performance. Meanwhile, these deep learning models fail to obtain good clustering results due to the large-scale and noise-containing characteristics of industrial nodes. In this paper, a large-scale graph clustering method (LsGCM) is proposed for cell conditions spatio-temporal localization in aluminum electrolysis to address the above issues. Specifically, a spatio-temporal graph construction method based on industrial process mechanism knowledge and local working condition boundary types statistical feature fusion is proposed for capturing effective spatio-temporal correlations between industrial nodes. Then, hysteresis knowledge of industrial production system is used to guide the nodes merging, thereby avoiding the incorrect merging of time-asynchronous nodes when performing the spatio-temporal region detection of local working conditions. Finally, combined with the actual spatio-temporal location information of industrial nodes, a novel spatio-temporal information expansion method (StIEM) of the sub-spatio-temporal graph describing local working condition is proposed for obtaining spatio-temporal feature information of the neighborhood, which is beneficial to improve the performance of industrial node clustering. Validation studies on a numerical simulation example and multiple real aluminum electrolysis industrial datasets certificate the effectiveness and superiority of the proposed method. In particular, compared with existing graph clustering methods, our method improves the clustering accuracy by 7.79%.