Graph Construction Method Research Articles

Learning Low-Rank Graph With Enhanced Supervision

In this paper, we propose a new semi-supervised graph construction method, which is capable of adaptively learning the similarity relationship between data samples by fully exploiting the potential of pairwise constraints, a kind of weakly supervisory information. Specifically, to adaptively learn the similarity relationship, we linearly approximate each sample with others under the regularization of the low-rankness of the matrix formed by the approximation coefficient vectors of all the samples. In the meanwhile, by taking advantage of the underlying local geometric structure of data samples that is empirically obtained, we enhance the dissimilarity information of the available pairwise constraints via propagation. We seamlessly combine the two adversarial learning processes to achieve mutual guidance. We cast our method as a constrained optimization problem and provide an efficient alternating iterative algorithm to solve it. Experimental results on five commonly-used benchmark datasets demonstrate that our method produces much higher classification accuracy than state-of-the-art methods, while running faster.

View graph construction for scenes with duplicate structures via graph convolutional network

View graph construction aims to effectively organise disordered image dataset through image retrieval technique before structure from motion (SfM). Existing view graph construction methods usually fail to handle scenes with duplicate structure, because these methods solely treat the construction of view graph as a process of image-pair-wise matching and lack in exploiting images' topological details in dataset. In this paper, we handle this problem from a novel perspective to construct view graph in a global paradigm by introducing an end-to-end graph convolutional network (GCN). First, a location-aware embedding module is introduced to encode images into a feature space that takes into account the feature's location by using Vision Transformer architecture, improving the distinction between features of duplicate structure. Second, graph convolutional network that consists of topological relationship preserving module and feature metric learning module is proposed. Topological relationship preserving network is proposed to help nodes maintain their connected neighbourhood features. By merging the topological connected information into images' embedding, our method can process image matching in a global mode, thus improving the disambiguation ability for images with duplicate scenes. Then a feature metric learning network is embedded into GCN to dynamically compute the linkage prediction among nodes based on their features. Finally, our method combines these three parts to jointly optimise nodes' features and linkage prediction in an end-to-end paradigm. We make qualitative and quantitative comparisons based on three public benchmark datasets and demonstrate that our proposed method performs favourably against other state-of-the-art methods.

Multi-view graph convolutional networks with attention mechanism

Recent advances in graph convolutional networks (GCNs), which mainly focus on how to exploit information from different hops of neighbors in an efficient way, have brought substantial improvement to many graph data modeling tasks. Most of the existing GCN-based models however are built on the basis of a fixed adjacency matrix, i.e., a single view topology of the underlying graph. That inherently limits the expressive power of the developed models especially when the raw graphs are often noisy or even incomplete due to the inevitably error-prone data measurement or collection. In this paper, we propose a novel framework, termed Multi-View Graph Convolutional Networks with Attention Mechanism (MAGCN), by incorporating multiple views of topology and an attention-based feature aggregation strategy into the computation of graph convolution. As an advanced variant of GCNs, MAGCN is fed with multiple “trustable” topologies, which already exist for a given task or are empirically generated by some classical graph construction methods, which has good potential to produce a better learning representation for downstream tasks. Furthermore, we present some theoretical analysis about the expressive power and flexibility of MAGCN, which provides a general explanation as to why multi-view based methods can potentially outperform those relying on a single view. Our experimental study demonstrates the state-of-the-art accuracies of MAGCN on Cora, Citeseer, and Pubmed datasets. Robustness analysis is also undertaken to show the advantage of MAGCN in handling some uncertainty issues in node classification tasks.

Method of Domain Knowledge Graph Construction Based on Property Graph Model

Method of Domain Knowledge Graph Construction Based on Property Graph Model

Adaptive Graph Representation for Clustering

Many graph construction methods cannot consider both local and global data structures in the construction of initial graph. Meanwhile, redundant features or even outliers and data with important characteristics are addressed equally in the graph optimization process. These lead to the learned representation graph may not capture the optimal structure. This paper proposes a novel graph learning method, called ACLWN, to overcome these problems. ACLWN is composed of an adaptive representation graph construction model named ARG, and an adaptive weighted sparse representation graph learning model named AWSG. In ARG, manifold learning and sparse representation are employed to capture the local structure of data. In AWSG, an adaptive weighted matrix is proposed to strengthen the important features and improve the robustness of the low-dimensional representation graph. Moreover, constraints such as non-negative low-rank, sparsity and distance regularization terms are imposed to capture the local and global structures of data. Comprehensive experimental results show that our method outperforms the compared state-of-the-art methods. The low-dimensional representation graph constructed by ACLWN is more suitable for clustering.

Method of intermodal accessibility graph construction

The article presents a method for modelling an intermodal graph of accessibility of urban areas. The accessibility of the city's territories is usually understood as a zone where a person can walk or get by transport for a certain time from a given point. Accessibility assessment is fundamental in the problems of computational urbanism and is used for a variety of applied spatial indexes and estimates. At the same time, traditional methods of assessing the transport accessibility of the urban environment require the creation of models of transport systems of the studied city, which is associated with significant costs. The situation is complicated by the peculiarities of the urban environment and the need to consider the movement of different types of transport in combination with walking. The method proposed in this article uses an alternative approach to assessing the accessibility of urban areas based on the construction of an intermodal accessibility graph. This makes it possible to use this algorithm in solving applied urban problems without the need to build complex transport models.

Semi-Supervised Superpixel-Based Multi-Feature Graph Learning for Hyperspectral Image Data

Graphs naturally lend themselves to model the complexities of Hyperspectral Image (HSI) data as well as to serve as semi-supervised classifiers by propagating given labels among nearest neighbours. In this work, we present a novel framework for the classification of HSI data in light of a very limited amount of labelled data, inspired by multi-view graph learning and graph signal processing. Given an a priori superpixel-segmented hyperspectral image, we seek a robust and efficient graph construction and label propagation method to conduct semi-supervised learning (SSL). Since the graph is paramount to the success of the subsequent classification task, particularly in light of the intrinsic complexity of HSI data, we consider the problem of finding the optimal graph to model such data. Our contribution is two-fold: firstly, we propose a multi-stage edge-efficient semi-supervised graph learning framework for HSI data which exploits given label information through pseudo-label features embedded in the graph construction. Secondly, we examine and enhance the contribution of multiple superpixel features embedded in the graph on the basis of pseudo-labels in an extension of the previous framework, which is less reliant on excessive parameter tuning. Ultimately, we demonstrate the superiority of our approaches in comparison with state-of-the-art methods through extensive numerical experiments.

Research on Event Logic Knowledge Graph Construction Method of Robot Transmission System Fault Diagnosis

Knowledge graph technology has important guiding significance for efficient and orderly fault diagnosis of robot transmission system. Taking the historical robot maintenance logs of robot transmission system as the research object, a top-down fault diagnosis event logic knowledge graph construction method is proposed. Firstly, we define event arguments of fault phenomenon and fault cause events, define event argument classes and relation between classes, and construct an event logic knowledge ontology model. According to the event logic knowledge ontology, the fault diagnosis event argument entity and relation in the corpus are labeled, and an event logic knowledge extraction dataset is formed. Secondly, an event argument entity and relation joint extraction model is proposed. Using stacked bidirectional long short-term memory(BiLSTM) to obtain deep context features of text. As a supplement to stacked BiLSTM, self-attention mechanism extracts character dependency features from multiple subspaces, and uses conditional random field(CRF) to realize entity recognition. The character dependency features are mapped to the entity label weight embedding, and spliced with deep context features to extract relations. Bidirectional graph convolutional network(BiGCN) is introduced for relation inference, graph convolution features are used to update deep context features to perform joint extraction in the second phase. Experimental results show that this method can improve the effect of event argument entity and relation joint extraction and is better than other methods. Finally, an event logic knowledge graph of robot transmission system fault diagnosis is constructed, which provides decision support for autonomous fault diagnosis of robot transmission system.

Automatic Requirements Classification Based on Graph Attention Network

Requirements classification is a significant task for requirements engineering, which is time-consuming and challenging. The traditional requirements classification models usually rely on manual pre-processing and have poor generalization capability. Moreover, these traditional models ignore the sentence structure and syntactic information in requirements. To address these problems, we propose an automatic requirements classification based BERT and graph attention network (GAT), called DBGAT. We construct dependency parse trees and then utilize the GAT for mining the implicit structure feature and syntactic feature of requirements. In addition, we introduce BERT to improve the generalization ability of the model. Experimental results of the PROMISE datasets demonstrate that our proposed DBGAT significantly outperforms existing state-of-the-art methods. Moreover, we investigate the impact of graph construction methods on non-functional requirements classification. DBGAT achieved the best classification results on both seen (F1-scores of up to 91%) and unseen projects (F1-scores of up to 88%), further demonstrating the strong generalization ability.

Knowledge Verification Method Based on Artificial Intelligence-based Knowledge Graph Construction

The knowledge graph connects real-world entities and concepts through their relationships, connects all different types of information to obtain a relationship network, and can analyze “relationship” issues. Creating a knowledge graph is a continuous process, and it needs to continuously learn new knowledge and update existing knowledge in the library as time and events change. However, since the accuracy of the updated new knowledge cannot be guaranteed, the new knowledge must be verified. This paper aims to study the knowledge verification method based on artificial intelligence-based knowledge graph construction. Based on the analysis of the knowledge graph construction process, the knowledge graph construction method and the knowledge verification method, knowledge verification is realized by constructing a probabilistic soft logic model. The experimental results show that the recall rate, F1 value, and AUC value of the candidate knowledge set are verified by the knowledge verification model proposed in this paper. Therefore, it can be inferred that the knowledge verification model proposed in this paper is effective.

Robust gravitation based adaptive [formula omitted]-NN graph under class-imbalanced scenarios

As a typical single parametric graph model, the k-Nearest Neighbor Graph (k-NNG) is characterized by its high efficiency in detecting topology information and remarkable capability for combining global and local features. However, graph-based supervised learning methods, including k-NNG, do not explicitly consider imbalanced class distribution; as a result, they often tend to perform vulnerable robustness in most imbalanced scenarios. This paper presents an adaptive k-NNG-based imbalanced classification method that can automatically determine the k value during graph construction. Our work presents two novel methodologies: (i) two types of adaptive graph construction methods to address the inherent complex characteristic of imbalanced class distribution; (ii) two graph-based gravitational classification rules to overcome the adverse bias towards the majority class in traditional KNN-based methods. The latter can effectively combine local nearest neighbors and subgraph information when calculating the gravitational force between pairs of vertices. Extensive experiments demonstrate the superiority of our method over other classification algorithms in imbalanced scenarios.

Subspace clustering via adaptive least square regression with smooth affinities

It has been proved that subspace clustering algorithms with weighted norm regularizers usually outperform their special cases with non-weighted regularizers. However, it is difficult to design suitable weighted regularizers for different types of subspace clustering algorithms. In this paper, we firstly provide an adaptive weighted norm regularizer construction strategy by using the recently proposed adaptive graph construction method. Secondly, we give a proposition that the affinities obtained by the adaptive graph construction method should be changed smoothly on the original data manifold. Hence, we devise a graph-constraint for the obtained affinity matrix. Thirdly, by integrating the above two techniques and least square regression (LSR) algorithm together, we design a new subspace clustering algorithm, called adaptive least square regression with smooth affinities (ALSR). For solving ALSR problem, we present an optimization algorithm whose computation burden and convergence are analyzed. Finally, plentiful experiments conducted on different types databases show the superiorities of ALSR.

The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study

Deep learning (DL)-based methods have advanced the field of Prognostics and Health Management (PHM) in recent years, because of their powerful feature representation ability. The data in PHM are typically regular data represented in the Euclidean space. Nevertheless, there are an increasing number of applications that consider the relationships and interdependencies of data and represent the data in the form of graphs. Such kind of irregular data in non-Euclidean space pose a huge challenge to the existing DL-based methods, making some important operations (e.g., convolutions) easily applied to Euclidean space but difficult to model graph data in non-Euclidean space. Recently, graph neural networks (GNNs), as the emerging neural networks, have been utilized to model and analyze the graph data. However, there still lacks a guideline on leveraging GNNs for realizing intelligent fault diagnostics and prognostics. To fill this research gap, a practical guideline is proposed in this paper, and a novel intelligent fault diagnostics and prognostics framework based on GNN is established to illustrate how the proposed guideline works. In this framework, three types of graph construction methods are provided, and seven kinds of graph convolutional networks (GCNs) with four different graph pooling methods are investigated. To afford benchmark results for helping further study, a comprehensive evaluation of these models is performed on eight datasets, including six fault diagnosis datasets and two prognosis datasets. Finally, four issues related to the performance of GCNs are discussed and potential research directions are provided. The code library is available at: https://github.com/HazeDT/PHMGNNBenchmark.

Multiple-view flexible semi-supervised classification through consistent graph construction and label propagation

Graph construction plays an essential role in graph-based label propagation since graphs give some information on the structure of the data manifold. While most graph construction methods rely on predefined distance calculation, recent algorithms merge the task of label propagation and graph construction in a single process. Moreover, the use of several descriptors is proved to outperform a single descriptor in representing the relation between the nodes. In this article, we propose a Multiple-View Consistent Graph construction and Label propagation algorithm (MVCGL) that simultaneously constructs a consistent graph based on several descriptors and performs label propagation over unlabeled samples. Furthermore, it provides a mapping function from the feature space to the label space with which we estimate the label of unseen samples via a linear projection. The constructed graph does not rely on a predefined similarity function and exploits data and label smoothness. Experiments conducted on three face and one handwritten digit databases show that the proposed method can gain better performance compared to other graph construction and label propagation methods.

A comparative study of pan-genome methods for microbial organisms: Acinetobacter baumannii pan-genome reveals structural variation in antimicrobial resistance-carrying plasmids.

Microbial organisms have diverse populations, where using a single linear reference sequence in comparative studies introduces reference-bias in downstream analyses, and leads to a failure to account for variability in the population. Recently, pan-genome graphs have emerged as an alternative to the traditional linear reference with many successful applications and a rapid increase in the number of methods available in the literature. Despite this enthusiasm, there has been no attempt at exploring these graph construction methods in depth, demonstrating their practical use. In this study, we aim to develop a general guide to help researchers who may want to incorporate pan-genomes in their analyses of microbial organisms. We evaluated the state-of-the art pan-genome construction tools to model a collection of 70 Acinetobacter baumannii strains. Our results suggest that all tools produced pan-genome graphs conforming to our expectations based on previous literature, and that their approach to homologue detection is likely to be the most influential in determining the final size and complexity of the pan-genome. The graphs overlapped most in the core pan-genome content while the cloud genes varied significantly among tools. We propose an alternative approach for pan-genome construction by combining two of the tools, Panaroo and Ptolemy, to further exploit them in downstream analyses, and demonstrate the effectiveness of our pipeline for structural variant calling in beta-lactam resistance genes in the same set of A. baumannii isolates, identifying various transposon structures for carbapenem resistance in chromosome, as well as plasmids. We identify a novel plasmid structure in two multidrug-resistant clinical isolates that had previously been studied, and which could be important for their resistance phenotypes.

Constructing a prior-dependent graph for data clustering and dimension reduction in the edge of AIoT

The Artificial Intelligence Internet of Things (AIoT) is an emerging concept aiming to perceive, understand and connect the ‘intelligent things’ to make the intercommunication of various networks and systems more efficient. A key step in achieving this goal is to carry out high-precision data analysis at the edge and cloud level. Clustering and dimensionality reduction in AIoT can facilitate efficient data management, storage, computing, and transmission of various data-driven AIoT applications. For high-efficiency data clustering and dimensionality reduction, this paper develops a prior-dependent graph (PDG) construction method to model and discover the complex relations of data. With the proper utilization and incorporation of data priors, i.e., (a) element local sparsity; (b) pair-wise symmetry; (c) multi-instance manifold smoothness; and (d) matrix low-rankness, the obtained graph has the characteristics of local sparsity, symmetry, low-rank, and can well reveal the complex multi-instance proximity among data points. The developed PDG model is then applied for two typical data analysis tasks, i.e., unsupervised data clustering and dimensionality reduction. Experimental results on multiple benchmark databases verify that, compared with some existing graph learning models, the PDG model can achieve substantial performance, which can be deployed in edge computing modules to provide efficient solutions for massive data management and applications in AIoT.

A Method for Constructing Geographical Knowledge Graph from Multisource Data

Global problems all occur at a particular location on or near the Earth’s surface. Sitting at the junction of artificial intelligence (AI) and big data, knowledge graphs (KGs) organize, interlink, and create semantic knowledge, thus attracting much attention worldwide. Although the existing KGs are constructed from internet encyclopedias and contain abundant knowledge, they lack exact coordinates and geographical relationships. In light of this, a geographical knowledge graph (GeoKG) construction method based on multisource data is proposed, consisting of a modeling schema layer and a filling data layer. This method has two advantages: (1) the knowledge can be extracted from geographic datasets; (2) the knowledge on multisource data can be represented and integrated. Firstly, the schema layer is designed to represent geographical knowledge. Then, the methods of extraction and integration from multisource data are designed to fill the data layer, and a storage method is developed to associate semantics with geospatial knowledge. Finally, the GeoKG is verified through linkage rate, semantic relationship rate, and application cases. The experiments indicate that the method could automatically extract and integrate knowledge from multisource data. Additionally, our GeoKG has a higher success rate of linking web pages with geographic datasets, and its exact coordinates have increased to 100%. This paper could bridge the distance between a Geographic Information System and a KG, thus facilitating more geospatial applications.

Knowledge graph construction based on knowledge enhanced word embedding model in manufacturing domain

Manufacturing industry is the foundation of a country’s economic development and prosperity. At present, the data in manufacturing enterprises have the problems of weak correlation and high redundancy, which can be solved effectively by knowledge graph. In this paper, a method of knowledge graph construction in manufacturing domain based on knowledge enhanced word embedding model is proposed. The main contributions are as follows: (1) At the algorithmic level, this paper proposes KEWE-BERT, an end-to-end model for joint entity and relation extraction, which superimposes the token embedding and knowledge embedding output by BERT and TransR so as to improve the effect of knowledge extraction; (2) At the application level, knowledge representation model ManuOnto and dataset ManuDT are constructed based on real manufacturing scenarios, and KEWE-BERT is used to construct knowledge graph from them. The knowledge graph constructed has rich semantic relations, which can be applied in actual production environment. Other than that, KEWE-BERT can extract effective knowledge and patterns from redundant texts in the enterprise, which providing a solution for enterprise data management.

Predicting User Activity Intensity Using Geographic Interactions Based on Social Media Check-In Data

Predicting user activity intensity is crucial for various applications. However, existing studies have two main problems. First, as user activity intensity is nonstationary and nonlinear, traditional methods can hardly fit the nonlinear spatio-temporal relationships that characterize user mobility. Second, user movements between different areas are valuable, but have not been utilized for the construction of spatial relationships. Therefore, we propose a deep learning model, the geographical interactions-weighted graph convolutional network-gated recurrent unit (GGCN-GRU), which is good at fitting nonlinear spatio-temporal relationships and incorporates users’ geographic interactions to construct spatial relationships in the form of graphs as the input. The model consists of a graph convolutional network (GCN) and a gated recurrent unit (GRU). The GCN, which is efficient at processing graphs, extracts spatial features. These features are then input into the GRU, which extracts their temporal features. Finally, the GRU output is passed through a fully connected layer to obtain the predictions. We validated this model using a social media check-in dataset and found that the geographical interactions graph construction method performs better than the baselines. This indicates that our model is appropriate for fitting the complex nonlinear spatio-temporal relationships that characterize user mobility and helps improve prediction accuracy when considering geographic flows.

Interactive Graph Construction for Graph-Based Semi-Supervised Learning.

Semi-supervised learning (SSL) provides a way to improve the performance of prediction models (e.g., classifier) via the usage of unlabeled samples. An effective and widely used method is to construct a graph that describes the relationship between labeled and unlabeled samples. Practical experience indicates that graph quality significantly affects the model performance. In this paper, we present a visual analysis method that interactively constructs a high-quality graph for better model performance. In particular, we propose an interactive graph construction method based on the large margin principle. We have developed a river visualization and a hybrid visualization that combines a scatterplot, a node-link diagram, and a bar chart to convey the label propagation of graph-based SSL. Based on the understanding of the propagation, a user can select regions of interest to inspect and modify the graph. We conducted two case studies to showcase how our method facilitates the exploitation of labeled and unlabeled samples for improving model performance.