Multiple Graphs Research Articles

A Novel Approach to Image Retrieval for Vision-Based Positioning Utilizing Graph Topology

Abstract. This research introduces a novel approach to improve vision-based positioning in the absence of GNSS signals. Specifically, we address the challenge posed by obstacles that alter image information or features, making retrieving the query image from the database difficult. While the Bag of Visual Words (BoVW) is a widely used image retrieval technique, it has a limitation in representing each image with a single histogram vector or vocabulary of visual words, i.e., the emergence of obstacles can introduce new features to the query image, resulting in different visual words. Our study overcomes this limitation by clustering the features of each image using the k-means method and generating a graph for each class. Each node or key point in the graph obtains additional information from its direct neighbors using functions employed in graph neural networks, functioning as a feedforward network with constant parameters. This process generates new embedding nodes, and eventually, global pooling is applied to produce one vector for each graph, representing each image with graph vectors based on objects or feature classes. As a result, each image is represented with graph vectors based on objects or feature classes. In the presence of obstacles covering one or more graphs, there is sufficient information from the query image to retrieve the most relevant image from the database. Our approach was applied to indoor positioning applications, with the database collected in Bolz Hall at The Ohio State University. Traditional BoVW techniques struggle to properly retrieve most query images from the database due to obstacles like humans or recently deployed objects that alter image features. In contrast, our approach has shown progress in image retrieval by representing each image with multiple graph vectors, depending on the number of objects in the image. This helps prevent or mitigate changes in image features caused by obstacles covering or adding features to the image, as demonstrated in the results.

Synergistic graph fusion via encoder embedding

In this paper, we introduce a method called graph fusion embedding, designed for multi-graph embedding with shared vertex sets. Under the framework of supervised learning, our method exhibits a remarkable and highly desirable synergistic effect: for sufficiently large vertex size, the accuracy of vertex classification consistently benefits from the incorporation of additional graphs. We establish the mathematical foundation for the method, including the asymptotic convergence of the embedding, a sufficient condition for asymptotic optimal classification, and the proof of the synergistic effect for vertex classification. Our comprehensive simulations and real data experiments provide compelling evidence supporting the effectiveness of our proposed method, showcasing the pronounced synergistic effect for multiple graphs from disparate sources.

Beyond Homophily and Homogeneity Assumption: Relation-Based Frequency Adaptive Graph Neural Networks.

Graph neural networks (GNNs) have been playing important roles in various graph-related tasks. However, most existing GNNs are based on the assumption of homophily, so they cannot be directly generalized to heterophily settings where connected nodes may have different features and class labels. Moreover, real-world graphs often arise from highly entangled latent factors, but the existing GNNs tend to ignore this and simply denote the heterogeneous relations between nodes as binary-valued homogeneous edges. In this article, we propose a novel relation-based frequency adaptive GNN (RFA-GNN) to handle both heterophily and heterogeneity in a unified framework. RFA-GNN first decomposes an input graph into multiple relation graphs, each representing a latent relation. More importantly, we provide detailed theoretical analysis from the perspective of spectral signal processing. Based on this, we propose a relation-based frequency adaptive mechanism that adaptively picks up signals of different frequencies in each corresponding relation space in the message-passing process. Extensive experiments on synthetic and real-world datasets show qualitatively and quantitatively that RFA-GNN yields truly encouraging results for both the heterophily and heterogeneity settings. Codes are publicly available at: https://github.com/LirongWu/RFA-GNN.

A complex network-based approach for resilient and flexible design resource allocation in industry 5.0

The development of Industry 5.0 focuses on customization, personalization in production, and the innovative thinking of employees, elevating the value of human contribution. Design, being an innovation-driven domain, demands greater flexibility in resource allocation. Consequently, rapidly and effectively allocating cloud service resources for personalized design tasks becomes crucial. With the emergence of the Industrial Metaverse, which blurs the boundaries between real and virtual design and manufacturing, it is gaining increasing attention. To embrace the advent of Industry 5.0 and the Industrial Metaverse, swift collaborative cloud services for design and manufacturing resources are essential. In this context, this article introduces a novel approach combining complex networks with the Non-dominated Sorting Genetic Algorithm III (NSGA-III), aimed at rapidly optimizing the dynamic allocation of distributed design resources (DRs). Initially, a multipartite graph is created from raw data and mapped to multiple bipartite graphs to identify key nodes in the network through intersection. Subsequently, these key nodes are used as reference points in the NSGA-III algorithm to achieve high-quality cloud service combinations, meeting the needs of design tasks with multiple subtasks, and related multi-objective optimization, including time, cost, reliability, maintainability, and reputation associated with the design. Finally, the Pareto service combinations obtained are used to construct a new complex network and employ the Girvan-Newman algorithm based on edge betweenness to identify community structures. In case of anomalies in the best service combination, alternative options can be swiftly searched from the identified communities, thereby enhancing the resilience of the cloud service process. Experimental results demonstrate the method's advantages in recovery and robustness, contributing significantly to the optimization of rapid cloud service allocation for DRs in the context of Industry 5.0.

Graph node matching for edit distance

Graphs are commonly used to model interactions between elements of a set, but computing the Graph Edit Distance between two graphs is an NP-complete problem that is particularly challenging for large graphs. To address this problem, we propose a supervised metric learning approach that combines Graph Neural Networks and optimal transport to learn an approximation of the GED in an end-to-end fashion. Our model consists of two siamese GNNs and a comparison block. Each graph pair’s nodes are augmented by positional encoding and embedded by multiple Graph Isomorphism Network layers. The obtained embeddings are then compared through a Multi-Layer Perceptron and Linear Sum Assignment Problem solver applied on a node-wise Euclidean metric defined in the embedding space. We show that our approach achieves state-of-the-art results on benchmark datasets and outperforms other similar works in the domain. Our approach also provides explainability through the extraction of an edit path from one graph to another and guarantees metric properties conservation during training and inference.

Saliency infused dialogue response generation: Improving task oriented text generation using feature attribution

Challenges persist in dialogue scenarios, particularly in multi-turn dialogues where response generation often disregards contextual information beyond the last user utterance, resulting in fluent yet inadequate responses. This paper addresses these issues by identifying and resolving common shortcomings in base model responses during response generation and proposes methods to enhance response quality in unannotated dialogue settings. Our approach involves augmenting information from multiple sources, including keywords, salient features, and knowledge graph triples. We compare the effectiveness of these methods against both the base model and human annotation, which includes dialogue acts and entities. Our findings demonstrate that appending extracted tokens significantly enhances response quality compared to annotated information. In task-oriented dialogue, models perform best when infused with saliency and knowledge graph triples, as shown in the MultiWOZ dataset. Conversely, focusing solely on saliency yields better results for open-domain dialogue, as demonstrated with the DailyDialog dataset. For contextual relevance, the information infusion could also approach the performance of the LLama2 model with only a tenth of the available parameters.

Developing a novel causal inference algorithm for personalized biomedical causal graph learning using meta machine learning

BackgroundModeling causality through graphs, referred to as causal graph learning, offers an appropriate description of the dynamics of causality. The majority of current machine learning models in clinical decision support systems only predict associations between variables, whereas causal graph learning models causality dynamics through graphs. However, building personalized causal graphs for each individual is challenging due to the limited amount of data available for each patient.MethodIn this study, we present a new algorithmic framework using meta-learning for learning personalized causal graphs in biomedicine. Our framework extracts common patterns from multiple patient graphs and applies this information to develop individualized graphs. In multi-task causal graph learning, the proposed optimized initial guess of shared commonality enables the rapid adoption of knowledge to new tasks for efficient causal graph learning.ResultsExperiments on one real-world biomedical causal graph learning benchmark data and four synthetic benchmarks show that our algorithm outperformed the baseline methods. Our algorithm can better understand the underlying patterns in the data, leading to more accurate predictions of the causal graph. Specifically, we reduce the structural hamming distance by 50-75%, indicating an improvement in graph prediction accuracy. Additionally, the false discovery rate is decreased by 20-30%, demonstrating that our algorithm made fewer incorrect predictions compared to the baseline algorithms.ConclusionTo the best of our knowledge, this is the first study to demonstrate the effectiveness of meta-learning in personalized causal graph learning and cause inference modeling for biomedicine. In addition, the proposed algorithm can also be generalized to transnational research areas where integrated analysis is necessary for various distributions of datasets, including different clinical institutions.

Constructing a Confidence-guided Multigraph Model for cognitive diagnosis in personalized learning

In modern education, personalized learning has garnered increasing attention, with cognitive diagnosis (CD) serving as a fundamental component. The objective of CD is to deeply comprehend students’ cognitive abilities, thereby identifying individual differences and providing support for personalized learning. However, many existing models ignore the influence of data noise and confidence in students’ responses. In addition, most existing methods equally extract evidence of students’ strengths and weaknesses from their overall responses, disregarding the characteristics of various types of relationships in students’ correct and incorrect responses. To this end, this study proposes a Confidence-guided Multigraph Model (CMM) for CD. First, to capture the changes and uncertainties in the student’s cognitive process, CMM dynamically calculates the confidence scores of the students’ responses. Second, CMM constructs multiple graphs to represent various relationships in students’ correct and incorrect responses. Then, CMM aggregates the unique information within the students’ correct and incorrect responses from various graphs. Finally, CMM uses a joint training strategy of multigraph iteration to simulate students’ cognitive ability in multiple dimensions. Extensive experimental results on two real-world datasets clearly demonstrate the efficacy of our proposed model. This innovative approach provides a novel perspective for the development of CD and lays the foundation for more accurate personalized learning support.

GAMA: A multi-graph-based anomaly detection framework for business processes via graph neural networks

Anomalies in business processes are inevitable for various reasons such as system failures and operator errors. Detecting anomalies is important for the management and optimization of business processes. However, prevailing anomaly detection approaches often fail to capture crucial structural information about the underlying process. To address this, we propose a multi-Graph based Anomaly detection fraMework for business processes via grAph neural networks, named GAMA. GAMA makes use of structural process information and attribute information in a more integrated way. In GAMA, multiple graphs are applied to model a trace in which each attribute is modeled as a separate graph. In particular, the graph constructed for the special attribute activity reflects the control flow. Then GAMA employs a multi-graph encoder and a multi-sequence decoder on multiple graphs to detect anomalies in terms of the reconstruction errors. Moreover, three teacher forcing styles are designed to enhance GAMA’s ability to reconstruct normal behaviors and thus improve detection performance. We conduct extensive experiments on both synthetic logs and real-life logs. The experiment results demonstrate that GAMA outperforms state-of-the-art methods for both trace-level and attribute-level anomaly detection.

Consistent graph learning for multi-view spectral clustering

Given the heterogeneous information of multiple views and the possible noise embedded in multi-view data, it is difficult to directly learn a consistent representation from multiple graphs to depict the intrinsic structure of all views. We propose a consistent graph learning method by exploiting both the high-order correlations underlying multiple views and the global structure of each single view. First, we calculate a transition probability matrix from each view. Second, a tensor is constructed by stacking each transition matrix as its frontal slice and then decomposed into the latent and error tensors. For the latent tensor, after rotated, a weighted tensor nuclear norm is used to encourage the rotate tensor to fully exploit the high-order correlations underlying multiple views. Furthermore, each frontal slice of the latent tensor is regularized by the nuclear norm to capture the global structure of each single view, and is restricted by probability constraints. Besides, we adopt the Frobenius-norm-based regularization to directly learn a common affinity matrix from the latent tensor. The established model is readily optimized by the alternating Lagrangian method. Extensive experiments on six real world datasets demonstrate that our method outperforms state-of-the-art methods.

Investment Decisions of the Individual Investors in the Capital Market of Bangladesh

Investment decisions of the individual investors in the capital market are influenced by various factors. Main objective of this study is to find out the influences of the factors on investment decisions of individual investors in the capital market in Bangladesh. A highly structured questionnaire has been used to collect primary data from 384 individual investors who are traded in the Dhaka Stock Exchange (DSE). The study respondents have been selected at a simple random method. Analysis of variance (ANOVA), multiple regression model, graphs, charts and tabular analysis have been used to analyze collected data and to test hypotheses of the study. The results showed that EPS has positive influence (β=0.0682, t=1.2439 and p=0.2143, test of hypothesis 2) on investment decisions and rank of EPS is 4 with mean score of 3.8099 and S.D=0.5087 (table 3). It has also found that dividend has positive relationship (β=0.0590, t=1.1054 and p=0.2697, test of hypothesis 3) with investment decisions and dividend is ranked 6 with mean score of 3.5755 and S.D=0.5593 (table 3). Accordingly, P/E ratio has a negative influence (β =-0.0069, t=-0.1341 and p=0.8934) on investment decisions of the individual investors. Therefore, this study will be very helpful to the individual investors to make correct investment decisions by analysing EPS, dividend trends and P/E ratio of the company.

Decoupled differentiable graph neural architecture search

The differentiable graph neural architecture search (GNAS) effectively designs graph neural networks (GNNs) efficiently and automatically with excellent performance based on different graph data distributions. Given a GNN search space containing multiple GNN component operation candidates, the differentiable GNAS method builds a mixed supernet using learnable architecture parameters multiplied by the GNN component operation candidates. When the mixed supernet completes optimization, the mixed supernet is pruned based on the best architecture parameters to efficiently identify the optimal GNN architecture in the GNN search space. However, the multiplicative relationship between the architecture parameters and the GNN component operation candidates introduces a coupled optimization bias into the weight optimization process of the mixed supernet GNN component operation candidates. This bias results in differentiable GNAS performance degradation. To solve the problem of coupled optimization bias in the previous differentiable GNAS method, we propose the Decoupled Differentiable Graph Neural Architecture Search (D2GNAS). It utilizes the Gumbel distribution as a bridge to decouple the weights optimization of supernet GNN component candidate operation and architecture parameters for constructing the decoupled differentiable GNN architecture sampler. The sampler is capable of selecting promising GNN architectures based on architecture parameters treated as sampling probabilities, and it is further optimized through the validation gradients derived from the sampled GNN architectures. Simultaneously, D2GNAS builds a single-path supernet with a pruning strategy to compress the supernet progressively to improve search efficiency further. We conduct extensive experiments on multiple benchmark graphs. The experimental findings demonstrate that D2GNAS outperforms all established baseline methods, both manual GNN and GNAS methods, in terms of performance. Additionally, D2GNAS has a lower time complexity than previous differentiable GNAS methods. Based on the fair GNN search space, it achieves an average 5x efficiency improvement. Codes are available at https://github.com/AutoMachine0/D2GNAS.

Graph ensemble neural network

Ensemble methods have been shown to improve graph neural networks (GNNs). Existing ensemble methods on graphs determine a strong classifier by combining a set of trained base classifiers, i.e., combining the final outputs of base classifiers for prediction. However, these methods fail to promote many popular GNNs to perform well under heterophily (in graphs where many connected nodes have different class labels), which limits their applicability. Furthermore, they ignore the hierarchical nature of GNNs, which results in no interaction between base classifiers when neighbors are aggregated (during training). Two issues arise from this: low applicability and shallow ensemble. We propose Graph Ensemble Neural Network (GEN) for addressing above issues, which is not a simple ensemble of GNNs, but instead integrates ensemble into GNNs to fuse a set of graphs. GEN deepens single ensemble into multiple ensembles during training and applies to homophily and heterophily graphs. In GEN, we design structure augmentation to generate some graphs for training and design feature augmentation for attenuating errors brought by the initial features. Different from existing graph ensemble methods that execute only one ensemble, GEN executes multiple deep ensembles throughout the neighbor aggregation to fuse multiple graphs generated by structure augmentation. Extensive experiments show that GEN achieves new state-of-the-art performance on homophily and heterophily graphs for the semi- and full-supervised node classification. The source code of GEN is publicly available at https://github.com/graphNN/GEN1.

Multi-Scale Dense Graph Attention Network for Hyperspectral Classification

In recent years, numerous deep learning-based methods have gained increasing attention in hyperspectral classification, particularly the Graph Neural Network, which exhibits superior capabilities in structural description. However, a single graph structure is not suitable for hyperspectral feature representation. Therefore, we propose a novel Multiple-Scale graph network structure, known as the Multi-Scale Dense Graph Attention network for hyperspectral classification. Firstly, semi-supervised local Fisher discriminant analysis and superpixel segmentation were employed for dimensionality reduction and multi-scale graph construction, respectively. Secondly, Spectral-Spatial convolution is applied to extract shallow features from the image. Subsequently, an improved graph self-attention network is sequentially applied to each scale graph, and the different scale graphs are densely connected through spatial feature alignment modules, designed using twice matrix multiplication. Finally, the combined pixel-level feature map from multiple graph spaces is derived, and Spectral-Spatial convolution is employed to fuse the abundant feature maps for hyperspectral classification. Experimental results on various hyperspectral datasets demonstrate the superiority of our MSDesGATnet over many state-of-the-art methods. The code is available at https://github.com/l7170/MSDesGAT.git.

DeepGCN based on variable multi‐graph and multimodal data for ASD diagnosis

AbstractDiagnosing individuals with autism spectrum disorder (ASD) accurately faces great challenges in clinical practice, primarily due to the data's high heterogeneity and limited sample size. To tackle this issue, the authors constructed a deep graph convolutional network (GCN) based on variable multi‐graph and multimodal data (VMM‐DGCN) for ASD diagnosis. Firstly, the functional connectivity matrix was constructed to extract primary features. Then, the authors constructed a variable multi‐graph construction strategy to capture the multi‐scale feature representations of each subject by utilising convolutional filters with varying kernel sizes. Furthermore, the authors brought the non‐imaging information into the feature representation at each scale and constructed multiple population graphs based on multimodal data by fully considering the correlation between subjects. After extracting the deeper features of population graphs using the deep GCN(DeepGCN), the authors fused the node features of multiple subgraphs to perform node classification tasks for typical control and ASD patients. The proposed algorithm was evaluated on the Autism Brain Imaging Data Exchange I (ABIDE I) dataset, achieving an accuracy of 91.62% and an area under the curve value of 95.74%. These results demonstrated its outstanding performance compared to other ASD diagnostic algorithms.

Spectral Graph Neural Network-Based Multi-Atlas Brain Network Fusion for Major Depressive Disorder Diagnosis.

Major Depressive Disorder (MDD) imposes a substantial burden within the healthcare domain, impacting millions of individuals worldwide. Functional Magnetic Resonance Imaging (fMRI) has emerged as a promising tool for the objective diagnosis of MDD, enabling the investigation of functional connectivity patterns in the brain associated with this disorder. However, most existing methods focus on a single brain atlas, which limits their ability to capture the complex, multi-scale nature of functional brain networks. To address these limitations, we propose a novel multi-atlas fusion method that incorporates early and late fusion in a unified framework. Our method introduces the concept of the holistic Functional Connectivity Network (FCN), which captures both intra-atlas relationships within individual atlases and inter-regional relationships between atlases with different brain parcellation scales. This comprehensive representation enables the identification of potential disease-related patterns associated with MDD in the early stage of our framework. Moreover, by decoding the holistic FCN from various perspectives through multiple spectral Graph Convolutional Neural Networks and fusing their results with decision-level ensembles, we further improve the performance of MDD diagnosis. Our approach is easily implemented with minimal modifications to existing model structures and demonstrates a robust performance across different baseline models. Our method, evaluated on public resting-state fMRI datasets, surpasses the current multi-atlas fusion methods, enhancing the accuracy of MDD diagnosis. The proposed novel multi-atlas fusion framework provides a more reliable MDD diagnostic technique. Experimental results show our approach outperforms both single- and multi-atlas-based methods, demonstrating its effectiveness in advancing MDD diagnosis.

Advancing UAV Sensor Fault Diagnosis based on Prior Knowledge and Graph Convolutional Network

Unmanned Aerial Vehicles (UAVs) are commonly equipped with multiple sensors to facilitate control and navigation. However, due to the complexity of the flight environment, the UAV sensors are prone to damage, which can cause serious accidents or even economic losses. Therefore, it is of great importance to propose an effective UAV sensor fault diagnosis method. The following weaknesses are obtained by the existing fault diagnosis methods: 1) The model-based methods, such as parameter estimation, state estimation, and equivalent space method, require introducing high-precision system models and expert knowledge. 2) Conventional graph convolutional network (GCN)-based methods fail to guarantee the accuracy of association graphs. To address the above two challenges, the dynamics model of quadrotor as prior knowledge is proposed in this paper to construct the association graph first. Then, a spatial-temporal difference graph convolutional network (STDGCN) consisting of a difference layer and multiple spatial-temporal graph convolutional modules is built. The difference layer enhances the feature extraction of the graph nodes, while the spatial-temporal graph convolutional modules extract the spatial-temporal dependencies of sensor data. Finally, the robustness and effectiveness of STDGCN are demonstrated in fault diagnosis compared with the commonly used data-driven methods. The experimental result shows that the proposed STDGCN method exhibits outstanding feature extraction ability with the highest diagnostic accuracy.

When decoupled GCN meets group discrimination: A special graph contrastive learning framework

While Graph Contrastive Learning (GCL) has demonstrated satisfactory outcomes, three main problems remain. First, to effectively transmit the message of higher-order hop nodes, it is imperative to stack multiple graph convolution layers, which results in heightened computational demands and memory requirements. Second, the traditional GCL framework employs the pairwise comparison of positive and negative samples, which could slow model training and necessitate considerable computing resources. Third, the GCL paradigm places considerable emphasis on the data augmentation. Some augmentation techniques focus on altering the graph’s structure, which demand significant computational resources. In order to resolve the aforementioned problems in GCL, we incorporate the decoupled GCN into GCL paradigm and develop a new GCL framework termed Decoupled Group Discrimination (DGD), which relies on a one-layer Multi-Layer Perceptron (MLP) encoder and entirely abandons GCN. We also put forward a new negative sample generation strategy which is customized for DGD and enriches the graph structure information during training. Furthermore, we identify a more effective approach to aggregate information from individual nodes by a range of learnable parameters. Experiments on various datasets for the node classification reveal that DGD yields the superior accuracy, faster training time, and less memory consumption. Specifically, DGD improves the overall accuracy of the node classification by a margin of 1 to 2 percentages with the time required for the model training diminished by over 90% and the memory reduced exceeding 70%.

Graph deep learning recognition of port ship behavior patterns from a network approach

The detection and recognition of ship mobile behavior patterns based on automatic identification system (AIS) data are crucial for ship navigation and maritime supervision. However, present methods, such as rule-based constraints and density clustering extraction, still suffer from restrictions imposed by artificial settings of parameters and thresholds. The lack of neighborhood context information in unstructured and serialized ship trajectory vector data makes it challenging to incorporate advanced methods such as deep learning for pattern learning. This study builds multiple semi-supervised deep learning graph neural network (GNN) models based on the message passing paradigm for recognizing ship mobile behavior patterns by constructing an AIS trajectory network and computing multi-order node features through Delaunay triangulation. It can get rid of the dependence on parameters of traditional rule-based and unsupervised learning methods. It also reduces the dependence on auxiliary information in trajectory qualitative by introducing multi-order node features. We conducted the experiments on cargo ship data from New York and Singapore to test our method. The model's classification accuracy is more than 99% for the New York dataset and more than 95% for the Singapore dataset. This method can be extended to other types of ships and traffic trajectory vector data with the excellent application potential of GNN in pattern recognition of vector mobile data. The code and experimental data are available at: https://github.com/destiny1103/DT-GNN.

A Survey of Multiple Kernel Graph Clustering Algorithms

In recent years, algorithms based on multi-kernel learning and graph clustering have garnered significant attention in the field of data mining. This article reviews four advanced multi-kernel graph clustering algorithms: nearest neighbor linear kernel weighted multi-kernel graph clustering, multi-kernel graph clustering based on simultaneous global and local structure preservation, multi-kernel graph clustering based on direct consensus relationship graph learning, and custom non-negative matrix factorization multi-kernel graph tensor clustering. These algorithms have their own characteristics and, by combining multi-kernel learning, graph clustering, and other advanced technologies, they improve the accuracy and efficiency of clustering. However, they also face challenges such as high computational complexity and parameter settings, necessitating further research and optimization. These algorithms have wide application prospects in fields such as image recognition, text classification, and bioinformatics, providing new solutions for handling complex data structures.