Graph Learning Algorithm Research Articles

Overview and advancement of power system topology addressing pre- and post-event strategies under abnormal operating conditions

The transition towards increased utilization of renewable energy and electric vehicles (EVs), along with the growing use of various other electrical devices, poses challenges to the stable and resilient operation of electric power systems (EPS), especially in the face of natural phenomena associated with climate change. This means that accurate topology and balanced EPS plays a key role to increase the capacity to respond quickly and in a coordinated manner to disaster situations such as cyber-attacks, earthquakes and floods. In this study, a new approach is presented to quickly and accurately detect topology attacks in EPS, thus contributing to making safer and more resilient. The proposed methods provide insights into maintaining uninterrupted electricity service by enabling EPS management through both post- and pre-event operational strategies. This approach is created by identifying faulty points with the obtained topology information and creating microgrid (MG) groups. Machine learning techniques have been integrated into the data intrusion attack detection (DIAD) system, enabling the detection of manipulated or faulty smart meters (SM). Concurrently, a topology identification (TI)-based graph learning algorithm is propounded to determine the exact fault locations before and after the event. For MV region restoration after determining the TI region, a mixed-integer linear programming (MILP) approach is employed to optimize the load restoration process in the MG regions. This approach aims to minimize losses and restore critical loads to their previous state as quickly as possible using flexible and emergency power balancing systems, including grid-support storage systems (GSSs), photovoltaic systems (PVs), electric vehicle charging stations (EVCS), and mobile generators. Moreover, a detailed compilation is presented under the topics of EPS topology, phase identification (PI) and its effect on power system resiliency (PSR), shedding light on the future development of EPS.

Learning bipartite graphs from spectral templates

Graph learning is crucial for understanding the relationship between data components. Signal processing-based graph learning algorithms are designed for specific signal models. This work investigates the problem of learning bipartite graphs given arbitrarily ordered spectral templates or graph eigenvectors. Starting from the spectral templates, the proposed algorithm identifies the vertex groups of the bipartite graph. Experiments conducted on three different types of synthetic datasets demonstrate that the proposed bipartite graph learning algorithms outperform structure-blind learning techniques across various signal-to-noise (SNR) regimes. Our algorithm leverages the spectral signatures of a bipartite graph, specifically the structure of the graph’s eigenvectors.

Optimal sensor placement for leak location in water distribution networks based on graph learning algorithm

Abstract The effective monitoring of urban water distribution networks (WDNs) relies heavily on pressure sensor placement. Nevertheless, a WDN may consist of hundreds of nodes, and it is not economically feasible to install sensors at each node. Therefore, how to identify an optimal location for sensor placement becomes a crucial issue. We use graph signal processing to analyze the pressure signals and introduce a framework for optimal sensor placement specifically designed for pressure signals. To address the limitation that pressure signals cannot be sampled directly, we propose a method to convert the signal into a band-limited signal that meets the requirements. Central to the method is learning a graph Fourier operator, and the effectiveness of the proposed method is proved theoretically. The graph Fourier operator enables the pressure data to become a smooth graph signal with variations in its topology. In addition, we design a graph filter based on the energy of the signal and obtain a band-limited signal that meets the requirements. To ensure the selection of representative nodes, we use a noise-robust graph sampling method to obtain the sensor node. Our method is further evaluated using the pressure data from Anytown versus Net3, showing strong performance in leak identification and signal reconstruction capabilities.

Consensus local graph for multiple kernel clustering

Due to the ability to represent the relationship among data, graph has received extensive attention in clustering field. As illustrated by existing studies, learning graph in kernel space is an effective way to capture the structure of data. Among kernel-based methods, multiple kernel learning (MKL) is increasingly popular since it can automatically utilize the complementary information contained in base kernels. Although many existing MKL-based graph learning algorithms have promising learning abilities, we observe that they (1) put too much attention on learning the consensus kernel which probably contains lots of redundant information and loses the diversity of base kernels; (2) ignore the local structure of the representations in multiple kernel spaces. To eliminate the bad effect of these issues, we propose a novel graph learning method, termed consensus local graph based on MKL (CLGMKL), for clustering. In CLGMKL, a low-rank kernel matrix is used to extract the discriminative information of each base kernel and a local graph is constructed to capture the local structure contained in each new kernel. Then CLGMKL combines these local graphs in a self-weighed way. Since the above processes are associated with each other, we jointly optimize them to obtain the overall optimality. An effective learning scheme with proved convergence is developed to optimize the combined objective function. Finally, extensive experiments on some popular datasets are conducted to test the effectiveness of the presented method. As illustrated, CLGMKL is more competitive than the state-of-the-art algorithms.

Exploring graph learning techniques for enhancing cross-domain applications in computer vision and natural language processing

With the rapid development of artificial intelligence, graph learning technology has become a research hotspot because of its unique data processing ability. This paper discusses the application of graph learning technology in computer vision (CV) and natural language processing (NLP), especially, it is applied to image segmentation and recognition, visual relationship detection, dynamic scene understanding, semantic role labeling and knowledge map enhancement. The graph neural network (GNN) can effectively learn the deep features of image or text data by defining pixels or hyperpixels as nodes and constructing the edges between nodes according to the spatial proximity or similarity between pixels. This paper also discusses the application of graph learning technology in improving model interpretability, including feature relation visualization, error analysis and diagnosis, and model decision path interpretation. By comparing the application effects of different graph learning models and algorithms, this paper aims to provide reference and inspiration for the follow-up research and application.

Integrating Knowledge Graph and Machine Learning Methods for Landslide Susceptibility Assessment

The suddenness of landslide disasters often causes significant loss of life and property. Accurate assessment of landslide disaster susceptibility is of great significance in enhancing the ability of accurate disaster prevention. To address the problems of strong subjectivity in the selection of assessment indicators and low efficiency of the assessment process caused by the insufficient application of a priori knowledge in landslide susceptibility assessment, in this paper, we propose a novel landslide susceptibility assessment framework by combing domain knowledge graph and machine learning algorithms. Firstly, we combine unstructured data, extract priori knowledge based on the Unified Structure Generation for Universal Information Extraction Pre-trained model (UIE) fine-tuned with a small amount of labeled data to construct a landslide susceptibility knowledge graph. We use Paired Relation Vectors (PairRE) to characterize the knowledge graph, then construct a target area characterization factor recommendation model by calculating spatial correlation, attribute similarity, Term Frequency–Inverse Document Frequency (TF-IDF) metrics. We select the optimal model and optimal feature combination among six typical machine learning (ML) models to construct interpretable landslide disaster susceptibility assessment mapping. Experimental validation and analysis are carried out on the three gorges area (TGA), and the results show the effectiveness of the feature factors recommended by the knowledge graph characterization learning, with the overall accuracy of the model after adding associated disaster factors reaching 87.2%. The methodology proposed in this research is a better contribution to the knowledge and data-driven assessment of landslide disaster susceptibility.

Aligned multi-view clustering for unmapped data via weighted tensor nuclear norm and adaptive graph learning

Multi-view clustering (MVC) is a prevailing clustering method that exploits consistency and complementarity among views to achieve satisfactory performance. The premise of MVC is that the samples of each view are mapped, that is, the same sample is placed in the same position among different views. However, multi-view data collected from the real world would also be unmapped, and thus conventional MVC methods are facing challenges. To address this problem, in our paper, we propose a novel aligned multi-view clustering (A-MVC) method for unmapped data. Specifically, the Calinski–Harabasz index is first employed to find the optimal view, and then the samples in other views are aligned to the samples in the optimal view with the help of the alignment matrix so that the unmapped data are converted into mapped ones. In addition, A-MVC absorbs the advantages of conventional multi-view clustering and employs both weighted tensor nuclear norm (TNN) and graph learning algorithms, which simultaneously learn the global representation and capture the local information. Finally, we integrate the alignment algorithm with a low-rank constraint based on weighted TNN and graph constraints into a unified framework. Extensive experimental results on certain unmapped multi-view datasets show that A-MVC outperforms other state-of-the-art methods. The codes and datasets are available at https://github.com/bingly/A-MVC.

Cognitive mapping and episodic memory emerge from simple associative learning rules

Episodic memory enables animals to map contexts and environmental features in space and time but is underused in artificial intelligence (AI). Here we show how simple associative learning rules can be expanded to basic episodic memory in AI. We augment an agent-based foraging simulation, ASIMOV, modeled on the simple neuronal circuitry of an invertebrate forager, by adding a novel computational module for simple episodic memory, the Feature Association Matrix (FAM). The FAM is a set of computationally light, graph learning algorithms which functionally resemble the auto- and hetero-associative circuits of the hippocampus for episodic memory. In simulations, FAM enables highly efficient foraging and navigation and shows how higher-order conditioning mechanisms give rise to spatial cognitive mapping by chaining pair-wise associations and encoding them with additional contexts. Thus, FAM demonstrates a biologically inspired, bottom-up enhancement of AI for higher-order cognition.

Knowledge graph learning algorithm based on deep convolutional networks

Knowledge graphs (KGs) serve as invaluable tools for organizing and representing structural information, enabling powerful data analysis and retrieval. In this paper, we propose a novel knowledge graph learning algorithm based on deep convolutional neural networks (KGLA-DCNN) to enhance the classification accuracy of KG nodes. Leveraging the hierarchical and relational nature of KGs, our algorithm utilizes deep convolutional neural networks to capture intricate patterns and dependencies within the graph. We evaluate the effectiveness of KGLA-DCNN on two benchmark datasets, Cora and Citeseer, renowned for their challenging node classification tasks. Through extensive experiments, we demonstrate that our proposed algorithm significantly improves classification accuracy compared to state-of-the-art methods, showcasing its capability to leverage the rich structural information inherent in KGs. The results highlight the potential of deep convolutional neural networks in enhancing the learning and representation capabilities of knowledge graphs, paving the way for more accurate and efficient knowledge discovery in diverse domains.

TREE-G: Decision Trees Contesting Graph Neural Networks

When dealing with tabular data, models based on decision trees are a popular choice due to their high accuracy on these data types, their ease of application, and explainability properties. However, when it comes to graph-structured data, it is not clear how to apply them effectively, in a way that in- corporates the topological information with the tabular data available on the vertices of the graph. To address this challenge, we introduce TREE-G. TREE-G modifies standard decision trees, by introducing a novel split function that is specialized for graph data. Not only does this split function incorporate the node features and the topological information, but it also uses a novel pointer mechanism that allows split nodes to use information computed in previous splits. Therefore, the split function adapts to the predictive task and the graph at hand. We analyze the theoretical properties of TREE-G and demonstrate its benefits empirically on multiple graph and vertex prediction benchmarks. In these experiments, TREE-G consistently outperforms other tree-based models and often outperforms other graph-learning algorithms such as Graph Neural Networks (GNNs) and Graph Kernels, sometimes by large margins. Moreover, TREE-Gs models and their predic tions can be explained and visualized.

Image and video analysis using graph neural network for Internet of Medical Things and computer vision applications

AbstractGraph neural networks (GNNs) have revolutionised the processing of information by facilitating the transmission of messages between graph nodes. Graph neural networks operate on graph‐structured data, which makes them suitable for a wide variety of computer vision problems, such as link prediction, node classification, and graph classification. The authors explore in depth the applications of GNNs in computer vision, including their design considerations, architectural challenges, applications, and implementation concerns. While conventional convolutional neural networks (CNNs) excel at object recognition in images and videos, GNN architectures offer a novel method for addressing various image and video comprehension challenges. A novel deep neural network‐based model for image and video analysis is proposed, which combines a neural network with fully connected layers on a graph. The proposed architecture extracts highly discriminative information from images and videos by leveraging the graph structure. Also, the investigation focuses on the enhancement of underlying connection network estimation using cutting‐edge graph learning algorithms. Experimental results on real‐world datasets demonstrate that the proposed GNN model is preferable to existing state‐of‐the‐art methods. It obtains a remarkable 96.63% accuracy on the ImageNet dataset, outperforming heuristic approaches, artificial neural networks, and conventional CNN techniques. From the results, we can see that GNNs are a potent instrument for graph data analysis and pave the way for machines to achieve human‐level visual intuition.

Blockchain Data Mining With Graph Learning: A Survey.

Blockchain data mining has the potential to reveal the operational status and behavioral patterns of anonymous participants in blockchain systems, thus providing valuable insights into system operation and participant behavior. However, traditional blockchain analysis methods suffer from the problems of being unable to handle the data due to its large volume and complex structure. With powerful computing and analysis capabilities, graph learning can solve the current problems through handling each node's features and linkage relationships separately and exploring the implicit properties of data from a graph perspective. This paper systematically reviews the blockchain data mining tasks based on graph learning approaches. First, we investigate the blockchain data acquisition method, integrate the currently available data analysis tools, and divide the sampling method into rule-based and cluster-based techniques. Second, we classify the graph construction into transaction-based blockchain and account-based methods, and comprehensively analyze the existing blockchain feature extraction methods. Third, we compare the existing graph learning algorithms on blockchain and classify them into traditional machine learning-based, graph representation-based, and graph deep learning-based methods. Finally, we propose future research directions and open issues which are promising to address.

Two-step multi-view data classification based on dynamic Graph-ELM

This paper focuses on the classification problem of multi-view data, aiming to improve the classification accuracy of current algorithms on multi-view data. Previous multi-view classification algorithms are usually based on exploiting the complementarity of different views and fusing features from different views. A representative category is the graph-based method, which builds a graph matrix for each view, and then fuses the graph matrices of different views to obtain a unified graph. These methods have the following problems: firstly, the graph matrix is simply based on sample similarity usually; secondly, the learned graph matrix does not change dynamically; thirdly, the weight of the graph representation matrix for a single view cannot be learned in the unified graph matrix. Therefore, this paper designs a Two-step classification algorithm based on Dynamic Graph-ELM, called TSDGELM. In the TSDGELM, the dynamic Graph-ELM is used to obtain the graph representation matrix of each view to save the local neighbor information of the data, and then a joint graph learning algorithm is designed based on the GBS (Graph-Based System) mechanism to fuse the graph matrix of the single-view, and finally the united graph is input into the classifier. To evaluate the effectiveness of the proposed method in this work, we conduct a series of experiments on eight datasets, and the results demonstrate the superiority of the proposed method.

Semantic knowledge-driven A-GASeq: A dynamic graph learning approach for assembly sequence optimization

In the context of an increasingly automated and personalized manufacturing mode, efficient assembly sequence planning (ASP) has emerged as a critical factor for enhancing production efficiency, ensuring product quality, and satisfying diverse market demands. To address this need, our study first transforms the assembly topology and process into a weighted precedence graph, wherein parts represent nodes, and the assembly interconnections between parts constitute weighted edges. Then, we formulate the quantitative models of semantic knowledge, encompassing three facets: assembly direction changes, assembly stability, and part assembly interference, and thus constructs a heuristic function. We propose a novel dynamic graph learning algorithm, i.e., assembly-oriented graph attention sequence (A-GASeq), utilizing the heuristic information as edge weights of the assembly graph structure to incrementally direct the search towards optimal sequences. The performance of A-GASeq is first evaluated utilizing three key metrics: area under the receiver operation characteristic curve (AUC), precision score, and time consumption. The results reveal the superiority of our model over competing state-of-the-art graph learning models using a real-world dataset. Concurrently, we apply the algorithm to actual industrial products of diverse complexity, thereby demonstrating its broad utility across different complex products and its potential for addressing complex assembly sequence planning problems in the field of smart manufacturing.

Multi-View Clustering With Graph Learning for scRNA-Seq Data.

Advances in single-cell biotechnologies have generated the single-cell RNA sequencing (scRNA-seq) of gene expression profiles at cell levels, providing an opportunity to study cellular distribution. Although significant efforts developed in their analysis, many problems remain in studying cell types distribution because of the heterogeneity, high dimensionality, and noise of scRNA-seq. In this study, a multi-view clustering with graph learning algorithm (MCGL) for scRNA-seq data is proposed, which consists of multi-view learning, graph learning, and cell type clustering. In order to avoid a single feature space of scRNA-seq being inadequate to comprehensively characterize the functions of cells, MCGL constructs the multiple feature spaces and utilizes multi-view learning to comprehensively characterize scRNA-seq data from different perspectives. MCGL adaptively learns the similarity graphs of cells that overcome the dependence on fixed similarity, transforming scRNA-seq analysis into the analysis of multi-view clustering. MCGL decomposes the networks of cells into view-specific and common networks in multi-view learning, which better characterizes the topological relationship of cells. MCGL simultaneously utilizes multiple types of cell-cell networks and fully exploits the connection relationship between cells through the complementarity between networks to improve clustering performance. The graph learning, graph factorization, and cell-type clustering processes are accomplished simultaneously under one optimization framework. The performance of the MCGL algorithm is validated with ten scRNA-seq datasets from different scales, and experimental results imply that the proposed algorithm significantly outperforms fourteen state-of-the-art scRNA-seq algorithms.

Incorporating park events into crime hotspot prediction on street networks: A spatiotemporal graph learning approach

Park events elevate crime risk in and around parks for brief periods by granting offenders close contact with abundant suitable targets in outdoor spaces. This study proposes to capture the formulated transient crime risk with a network-based feature, Park Event Density (PED), that monitors the dynamic event density across parks. We incorporate the PED into various crime hotspot prediction models to test its effectiveness. The sample includes all the robbery(n = 1555) and theft(n = 22596) incidents between 2016 and 2018 in the Center Side of Chicago. We generate daily and intraday crime hotspot predictions using two spatiotemporal graph learning algorithms (i.e., Graph Wavenet and Spatiotemporal Graph Convolution Neural Networks) and a traditional counterpart (i.e., LSTM). The results reveal that the PED-incorporated models have up to 25% higher accuracy, particularly in the intraday theft predictions. Another significant result indicates that the predictive accuracies of spatiotemporal graph learning algorithms are up to three times higher than their traditional counterpart. The proposed method provides additional information to security decision-makers with crime hotspot prediction models sensitive to the changing crime risk landscape across a region during park events. It also helps organize safer outdoor public events by enacting timely security interventions through more accurate crime hotspot predictions.

An Improved Algorithm for Topology Identification of Distribution Networks Using Smart Meter Data and Its Application for Fault Detection

This paper proposes a new method for estimating the topology of radial distribution networks and a novel data-driven fault detection technique using smart meter data. An improved method to estimate voltage sensitivity coefficients from smart meter data is proposed that takes into account the variability of the transformer voltage. These coefficients are used in both the topology estimation and the fault detection algorithms. In the topology estimation algorithm, an improved graph learning algorithm, which iteratively constructs the network graph, is devised. In the fault detection algorithm, the objective is to look for sudden changes in the estimated voltage sensitivity coefficients. The performance of the proposed methods is first assessed on randomly generated topologies under various noise conditions. Then, the performance of the algorithms is validated using real smart meter measurements obtained from Australian distribution networks. The results show a significant improvement in the accuracy of estimated topologies compared to the state-of-the-art methods while the fault detection technique is successful in detecting faults using real smart meter data.

Multiresolution graph transformers and wavelet positional encoding for learning long-range and hierarchical structures.

Contemporary graph learning algorithms are not well-suited for large molecules since they do not consider the hierarchical interactions among the atoms, which are essential to determining the molecular properties of macromolecules. In this work, we propose Multiresolution Graph Transformers (MGT), the first graph transformer architecture that can learn to represent large molecules at multiple scales. MGT can learn to produce representations for the atoms and group them into meaningful functional groups or repeating units. We also introduce Wavelet Positional Encoding (WavePE), a new positional encoding method that can guarantee localization in both spectral and spatial domains. Our proposed model achieves competitive results on three macromolecule datasets consisting of polymers, peptides, and protein-ligand complexes, along with one drug-like molecule dataset. Significantly, our model outperforms other state-of-the-art methods and achieves chemical accuracy in estimating molecular properties (e.g., highest occupied molecular orbital, lowest unoccupied molecular orbital, and their gap) calculated by Density Functional Theory in the polymers dataset. Furthermore, the visualizations, including clustering results on macromolecules and low-dimensional spaces of their representations, demonstrate the capability of our methodology in learning to represent long-range and hierarchical structures. Our PyTorch implementation is publicly available at https://github.com/HySonLab/Multires-Graph-Transformer.

TC-GATN: Temporal Causal Graph Attention Networks With Nonlinear Paradigm for Multivariate Time-Series Forecasting in Industrial Processes

Multivariate time series (MTS) forecasting plays an important role in industrial process monitoring, control and optimizations. Usually, hierarchical interactive behaviors among industrial MTS have formed complex nonlinear causal characteristics, which greatly hinders the applications of existing predictive models. It is found that graph attention networks (GAT) provide technical ideas to meet this challenge. However, the unknown directed graph and linear conversions of node information make conventional GAT less popular for the industrial fields. In this paper, we propose a novel prediction model termed as temporal causal graph attention networks with nonlinear paradigms (TC-GATN) to adequately capture inherent dependencies on industrial MTS. Specifically, the graph learning algorithm concerning the granger causality (GC) is exploited to extract potential relationships among multiple variables for guiding directional edge connections of the hierarchy. Then, parallel GRU encoders located in the graph neighborhood space are introduced to perform the nonlinear interaction of node features, which accomplishes the adaptive transformation and transmission. The self-attention mechanism is further employed to aggregate encoder hidden states across all stages. Finally, a temporal module is supplemented to process information from the graph layer, achieving satisfactory predictions. The feasibility and effectiveness of the TC-GATN are validated by two actual datasets from the methanol production and the chlorosilane distillation.

BejaGNN: behavior-based Java malware detection via graph neural network.

As a popular platform-independent language, Java is widely used in enterprise applications. In the past few years, language vulnerabilities exploited by Java malware have become increasingly prevalent, which cause threats for multi-platform. Security researchers continuously propose various approaches for fighting against Java malware programs. The low code path coverage and poor execution efficiency of dynamic analysis limit the large-scale application of dynamic Java malware detection methods. Therefore, researchers turn to extracting abundant static features to implement efficient malware detection. In this paper, we explore the direction of capturing malware semantic information by using graph learning algorithms and present BejaGNN (Behavior-based Java malware detection via Graph Neural Network), a novel behavior-based Java malware detection method using static analysis, word embedding technique, and graph neural network. Specifically, BejaGNN leverages static analysis techniques to extract ICFGs (Inter-procedural Control Flow Graph) from Java program files and then prunes these ICFGs to remove noisy instructions. Then, word embedding techniques are adopted to learn semantic representations for Java bytecode instructions. Finally, BejaGNN builds a graph neural network classifier to determine the maliciousness of Java programs. Experimental results on a public Java bytecode benchmark demonstrate that BejaGNN achieves high F1 98.8% and is superior to existing Java malware detection approaches, which verifies the promise of graph neural network in Java malware detection.