Latent Graph Research Articles

An interactive clustering method via metric learning for analyzing energy consumption patterns

Accurate analysis of energy consumption patterns is the key to achieving the goal of sustainable building energy efficiency, and clustering analysis in data mining techniques has shown efficacy in this regard. However, traditional clustering methods suffer from several issues including lack of users’ participation and low quality of results. To address these challenges, this paper proposes an interactive clustering method based on metric learning. It allows users to interact with clustering models by manipulating initial clusters and inject their domain knowledge for quality improvement. Meanwhile, a metric learning technique is applied to learn a distance metric based on the initial clustering results to improve the quality and flexibility of clustering. Accordingly, a latent graph that imitates the proximity of consumers can be constructed to propagate the clustering intent of users to larger unseen data. In collaboration with five experts in the field of building energy consumption, case studies demonstrate that our method can effectively recognize four types of daily consumption patterns. Compared with the classical k-means method, the mean variance of data features, the Davies-Bouldin Index (DBI) has decreased by 11.19 % and 21.54 %, respectively, and the Calinski-Harabasz (CH) has improved by 10.72 %.

Optimizing latent graph representations of surgical scenes for unseen domain generalization.

Advances in deep learning have resulted in effective models for surgical video analysis; however, these models often fail to generalize across medical centers due to domain shift caused by variations in surgical workflow, camera setups, and patient demographics. Recently, object-centric learning has emerged as a promising approach for improved surgical scene understanding, capturing and disentangling visual and semantic properties of surgical tools and anatomy to improve downstream task performance. In this work, we conduct a multicentric performance benchmark of object-centric approaches, focusing on critical view of safety assessment in laparoscopic cholecystectomy, then propose an improved approach for unseen domain generalization. We evaluate four object-centric approaches for domain generalization, establishing baseline performance. Next, leveraging the disentangled nature of object-centric representations, we dissect one of these methods through a series of ablations (e.g., ignoring either visual or semantic features for downstream classification). Finally, based on the results of these ablations, we develop an optimized method specifically tailored for domain generalization, LG-DG, that includes a novel disentanglement loss function. Our optimized approach, LG-DG, achieves an improvement of 9.28% over the best baseline approach. More broadly, we show that object-centric approaches are highly effective for domain generalization thanks to their modular approach to representation learning. We investigate the use of object-centric methods for unseen domain generalization, identify method-agnostic factors critical for performance, and present an optimized approach that substantially outperforms existing methods.

ALZHEIMER’S DISEASE DETECTION USING DEEP LEARNING

Image processing is a technique for applying various procedures to a picture in order to improve it or extract some relevant information from it. It is a kind of signal processing where the input is an image and the output may either be another picture or features or characteristics related to that image. Image processing is one of the technologies that is currently expanding quickly. It is a primary subject of research in both the engineering and computer science fields. For dementia, Alzheimer's disease (AD) is the most prevalent kind. It often shows itself as a steadily declining memory and cognitive function, which makes it difficult for the affected person to live independently and has a significant negative influence on both the affected personand society. At the moment, AD diagnosis depends on medical history analysis, blood testing, behavior analysis, brain imaging, and cognitive testing. But because these processes are arbitrary and uneven, it is difficult to provide a precise forecast for the early phases of AD challenging. A dynamic dual-graph fusion convolutional network is suggested in this paper to enhance the accuracy of Alzheimer's disease (AD) diagnosis. The key contributions of the paper are as follows: The proposed architecture can dynamically adjust the graph structure for GCN to produce better diagnosis outcomes by learning the optimal underlying latent graph, propose a novel dynamic GCN architecture, which is an end-to-end pipeline for diagnosing AD, incorporate feature graph learning and dynamic graph learning, giving those useful features of subjects more weight while reducing the weights of other noise features. Experiments show that our approach achieves great classification results in AD diagnosis while offering flexibility and stability. This project is implemented for the Alzheimer disease classification using Graph convolutional network architecture like CNN with LSTM layer and fit the model in the training and testing and deploy the model for getting the test image output and then compare the accuracy of the model for getting the most perfect model for medical image classification and get theaccuracy of CNN- LSTM layer with 98%.

Deep Convolutional Curvelet Transform- Based MRI Approach for Early Detection of ALZHEIMER' S Disease

Image processing is a technique for applying various procedures to a picture in order to improve it or extract some relevant information from it. It is a kind of signal processing where the input is an image and the output may either be another picture or features or characteristics related to that image. Image processing is one of the technologies that is currently expanding quickly. It is a primary subject of research in both the engineering and computer science fields. For dementia, Alzheimer's disease (AD) is the most prevalent kind. It often shows itself as a steadily declining memory and cognitive function, which makes it difficult for the affected person to live independently and has a significant negative influence on both the affected person and society. At the moment, AD diagnosis depends on medical history analysis, blood testing, behavior analysis, brain imaging, and cognitive testing. But because these processes are arbitrary and uneven, it is difficult to provide a precise forecast for the early phases of AD challenging. A dynamic dual-graph fusion convolutional network is suggested in this paper to enhance the accuracy of Alzheimer's disease (AD) diagnosis. The key contributions of the paper are as follows: The proposed architecture can dynamically adjust the graph structure for GCN to produce better diagnosis outcomes by learning the optimal underlying latent graph, propose a novel dynamic GCN architecture, which is an end-to-end pipeline for diagnosing AD, incorporate feature graph learning and dynamic graph learning, giving those useful features of subjects more weight while reducing the weights of other noise features. Experiments show that our approach achieves great classification results in AD diagnosis while offering flexibility and stability. This project is implemented for the Alzheimer disease classification using Graph convolutional network architecture like CNN with LSTM layer and fit the model in the training and testing and deploy the model for getting the test image output and then compare the accuracy of the model for getting the most perfect model for medical image classification and get the accuracy of CNN- LSTM layer with 98%.

Hierarchical spatial–temporal autocorrelation graph neural network for online wind turbine pitch system fault detection

The advancement of low-cost, non-manually labeled big data technologies for fault detection in wind turbines is crucial to guarantee their safe and efficient operation. In this context, Normal Behavior Modelling (NBM) is a prevalent approach. However, existing NBM methods for wind turbine fault detection inadequately utilize complex spatial–temporal correlations within the Supervisory Control and Data Acquisition (SCADA) during the normal behavior prediction stage. To cope with this limitation, this paper propose a hierarchical spatial-temporal autocorrelation graph neural network method for online wind turbine pitch system fault detection. This approach integrates a dynamic graph network with an adaptive structure for spatial correlation learning and a transformer model with autocorrelation attention to identify periodic time-distance correlations. Furthermore, a hierarchical neural network, specifically designed for wind turbine physical structure, enhances local information extraction through seven latent graph neural networks and a probsparse attention mechanism. The proposed method demonstrates significant effectiveness in real-world applications, as evidenced by data from a Shanghai wind farm.

Adaptive Feature Imputation with Latent Graph for Deep Incomplete Multi-View Clustering

In recent years, incomplete multi-view clustering (IMVC), which studies the challenging multi-view clustering problem on missing views, has received growing research interests. Previous IMVC methods suffer from the following issues: (1) the inaccurate imputation for missing data, which leads to suboptimal clustering performance, and (2) most existing IMVC models merely consider the explicit presence of graph structure in data, ignoring the fact that latent graphs of different views also provide valuable information for the clustering task. To overcome such challenges, we present a novel method, termed Adaptive feature imputation with latent graph for incomplete multi-view clustering (AGDIMC). Specifically, it captures the embbedded features of each view by incorporating the view-specific deep encoders. Then, we construct partial latent graphs on complete data, which can consolidate the intrinsic relationships within each view while preserving the topological information. With the aim of estimating the missing sample based on the available information, we utilize an adaptive imputation layer to impute the embedded feature of missing data by using cross-view soft cluster assignments and global cluster centroids. As the imputation progresses, the portion of complete data increases, contributing to enhancing the discriminative information contained in global pseudo-labels. Meanwhile, to alleviate the negative impact caused by inferior impute samples and the discrepancy of cluster structures, we further design an adaptive imputation strategy based on the global pseudo-label and the local cluster assignment. Experimental results on multiple real-world datasets demonstrate the effectiveness of our method over existing approaches.

Multi-view clustering via pseudo-label guide learning and latent graph structure recovery

Multi-view clustering (MvC) accomplishes sample classification tasks by exploring information from different views. Currently, researchers have paid greater attention to graph-based MvC methods. However, most existing methods only consider the original graph structure and pay relatively little attention to the graph structure in the latent space. In addition, most methods need to pay more attention to the consistency of information on different labels. Otherwise, this may lead to the loss of label information. This paper presents a new multi-view clustering framework to address the above issues. The proposed method considers both the information in the latent space and the original data space, which firstly obtains the pseudo-label by latent representation learning and then lets the pseudo-label guide the learning of the complementary information between the raw data views. To ensure the integrity of the data structure, a latent graph structure recovery strategy is designed in the latent space. Finally, an enhanced label fusion strategy is designed to fusion the different types of labels, yielding an information-rich label matrix for clustering. Experimental results demonstrate the proposed method’s effectiveness compared to other advanced approaches.

Bayesian graph convolutional network for traffic prediction

Recently, adaptive graph convolutional network based traffic prediction methods, learning a latent graph structure from traffic data via various attention-based mechanisms, have achieved impressive performance. However, they are still limited to finding a better description of spatial relationships between traffic conditions due to: (1) ignoring the prior of the observed road network topology; (2) neglecting the presence of negative spatial relationships; and (3) lacking investigation on the uncertainty of the graph structure. In this paper, we propose a Bayesian Graph Convolutional Network (BGCN) framework to alleviate these issues. Under this framework, the graph structure is viewed as a random realization from a parametric generative model, and its posterior is inferred using the observed topology of the road network and traffic data. Specifically, the parametric generative model is comprised of two parts: (1) a constant adjacency matrix that discovers potential spatial relationships from the observed physical connections between roads using a Bayesian approach; (2) a learnable adjacency matrix that learns globally shared spatial correlations from traffic data in an end-to-end fashion and can model negative spatial correlations. The posterior of the graph structure is then approximated by performing Monte Carlo dropout on the parametric graph structure. We verify the effectiveness of our method on five real-world datasets, and the experimental results demonstrate that BGCN attains superior performance compared with state-of-the-art methods. The source code is available at https://github.com/JunFu1995/BGCN.git.

Latent Graph Representations for Critical View of Safety Assessment.

Assessing the critical view of safety in laparoscopic cholecystectomy requires accurate identification and localization of key anatomical structures, reasoning about their geometric relationships to one another, and determining the quality of their exposure. Prior works have approached this task by including semantic segmentation as an intermediate step, using predicted segmentation masks to then predict the CVS. While these methods are effective, they rely on extremely expensive ground-truth segmentation annotations and tend to fail when the predicted segmentation is incorrect, limiting generalization. In this work, we propose a method for CVS prediction wherein we first represent a surgical image using a disentangled latent scene graph, then process this representation using a graph neural network. Our graph representations explicitly encode semantic information - object location, class information, geometric relations - to improve anatomy-driven reasoning, as well as visual features to retain differentiability and thereby provide robustness to semantic errors. Finally, to address annotation cost, we propose to train our method using only bounding box annotations, incorporating an auxiliary image reconstruction objective to learn fine-grained object boundaries. We show that our method not only outperforms several baseline methods when trained with bounding box annotations, but also scales effectively when trained with segmentation masks, maintaining state-of-the-art performance.

DSANet: Dynamic and Structure-Aware GCN for Sparse and Incomplete Point Cloud Learning.

Learning 3-D structures from incomplete point clouds with extreme sparsity and random distributions is a challenge since it is difficult to infer topological connectivity and structural details from fragmentary representations. Missing large portions of informative structures further aggravates this problem. To overcome this, a novel graph convolutional network (GCN) called dynamic and structure-aware NETwork (DSANet) is presented in this article. This framework is formulated based on a pyramidic auto-encoder (AE) architecture to address accurate structure reconstruction on the sparse and incomplete point clouds. A PointNet-like neural network is applied as the encoder to efficiently aggregate the global representations of coarse point clouds. On the decoder side, we design a dynamic graph learning module with a structure-aware attention (SAA) to take advantage of the topology relationships maintained in the dynamic latent graph. Relying on gradually unfolding the extracted representation into a sequence of graphs, DSANet is able to reconstruct complicated point clouds with rich and descriptive details. To associate analogous structure awareness with semantic estimation, we further propose a mechanism, called structure similarity assessment (SSA). This method allows our model to surmise semantic homogeneity in an unsupervised manner. Finally, we optimize the proposed model by minimizing a new distortion-aware objective end-to-end. Extensive qualitative and quantitative experiments demonstrate the impressive performance of our model in reconstructing unbroken 3-D shapes from deficient point clouds and preserving semantic relationships among different regional structures.

An Adaptive Region-Based Transformer for Nonrigid Medical Image Registration With a Self-Constructing Latent Graph.

Nonrigid registration of medical images is formulated usually as an optimization problem with the aim of seeking out the deformation field between a referential-moving image pair. During the past several years, advances have been achieved in the convolutional neural network (CNN)-based registration of images, whose performance was superior to most conventional methods. More lately, the long-range spatial correlations in images have been learned by incorporating an attention-based model into the transformer network. However, medical images often contain plural regions with structures that vary in size. The majority of the CNN-and transformer-based approaches adopt embedding of patches that are identical in size, disallowing representation of the inter-regional structural disparities within an image. Besides, it probably leads to the structural and semantical inconsistencies of objects as well. To address this issue, we put forward an innovative module called region-based structural relevance embedding (RSRE), which allows adaptive embedding of an image into unequally-sized structural regions based on the similarity of self-constructing latent graph instead of utilizing patches that are identical in size. Additionally, a transformer is integrated with the proposed module to serve as an adaptive region-based transformer (ART) for registering medical images nonrigidly. As demonstrated by the experimental outcomes, our ART is superior to the advanced nonrigid registration approaches in performance, whose Dice score is 0.734 on the LPBA40 dataset with 0.318% foldings for deformation field, and is 0.873 on the ADNI dataset with 0.331% foldings.

Bayesian Learning of Graph Substructures

Graphical models provide a powerful methodology for learning the conditional independence structure in multivariate data. Inference is often focused on estimating individual edges in the latent graph. Nonetheless, there is increasing interest in inferring more complex structures, such as communities, for multiple reasons, including more effective information retrieval and better interpretability. Stochastic blockmodels offer a powerful tool to detect such structure in a network. We thus propose to exploit advances in random graph theory and embed them within the graphical models framework. A consequence of this approach is the propagation of the uncertainty in graph estimation to large-scale structure learning. We consider Bayesian nonparametric stochastic blockmodels as priors on the graph. We extend such models to consider clique-based blocks and to multiple graph settings introducing a novel prior process based on a Dependent Dirichlet process. Moreover, we devise a tailored computation strategy of Bayes factors for block structure based on the Savage-Dickey ratio to test for presence of larger structure in a graph. We demonstrate our approach in simulations as well as on real data applications in finance and transcriptomics.

Hierarchical Graph Convolutional Networks With Latent Structure Learning for Mechanical Fault Diagnosis

Industrial sensor signals are essentially non-Euclidean graph structures due to the interplay between process variables; thus, graph convolutional networks (GCNs) have been widely studied and applied. However, most of the existing GCN-based methods may suffer from two drawbacks: 1) it is difficult to characterize multiple interactions among nodes and 2) the input graph constructed from the original data may contain errors and missing edges, which will degenerate the fault diagnosis performance. To address the abovementioned issues, this article designs a hierarchical GCN with latent structure learning for industrial fault diagnosis, which can organize hierarchical networks to collaboratively improve the quality of latent graph structure, and enhanced diagnostic performance can be guaranteed. First, a high-quality updated graph is formed by incorporating the original graph with the new graph in the graph constructing layer, which can not only eliminate the adverse effects of noise and outliers but also characterize the multiple interactions among nodes. Then, the updated graph is fed into the multilayer GCN layer for better feature learning and enhances the node representation through intra- and inter-layer convolutional operations simultaneously. After that, the produced node embeddings are used to guide the latent structure learning process for optimal graph. Finally, the proposed method is verified in both the simulated and real industrial processes. The experimental results demonstrate that the new approach has better fault diagnosis accuracy and practicability than state-of-the-art methods.

Span-based dependency-enhanced graph convolutional network for aspect sentiment triplet extraction

Aspect sentiment triplet extraction task detects three elements of fine-grained sentiment analysis from given sentence, including aspect and opinion terms and their sentiment polarity. Existing methods mainly include tagging-based and span-based methods, where the former show defects on handling overlapped triplets, and the latter could theoretically handle all overlapped triplets but lack of tailored inter-word dependency so that suffer from insufficient span semantic. In this paper, we propose a span-based dependency-enhanced graph convolutional network, which leverages contextual semantic and latent dependency to enrich span representations. Specifically, we devise a latent graph convolutional network to emphasize critical inter-word dependencies and cut off redundant connections in a learnable gating manner, improving the information flow during inter-word interaction. In addition, considering the problem of multi-word term sentiment consistency, we detect effective aspect and opinion terms derived from the output of span enumeration, and introduce term-level interactions by coupling, which meanwhile enables our model to deal with various types of triplets including many-to-one and one-to-many overlapped triplets. Extensive experiments over four benchmark datasets verify that the proposed method outperforms all the baselines with an average F1 improvement of up to 6.13%, and meanwhile shows fine interpretability. The experimental results demonstrate that effectively enhancing token-level and term-level interactions can significantly improve the aspect sentiment triplet extraction performance.

Multiscale graph neural network autoencoders for interpretable scientific machine learning

The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN) autoencoding architecture with demonstrations on complex fluid flow applications. To address the first goal of interpretability, the GNN autoencoder achieves reduction in the number nodes in the encoding stage through an adaptive graph reduction procedure. This reduction procedure essentially amounts to flowfield-conditioned node sampling and sensor identification, and produces interpretable latent graph representations tailored to the flowfield reconstruction task in the form of so-called masked fields. These masked fields allow the user to (a) visualize where in physical space a given latent graph is active, and (b) interpret the time-evolution of the latent graph connectivity in accordance with the time-evolution of unsteady flow features (e.g. recirculation zones, shear layers) in the domain. To address the goal of unstructured mesh compatibility, the autoencoding architecture utilizes a series of multi-scale message passing (MMP) layers, each of which models information exchange among node neighborhoods at various lengthscales. The MMP layer, which augments standard single-scale message passing with learnable coarsening operations, allows the decoder to more efficiently reconstruct the flowfield from the identified regions in the masked fields. Analysis of latent graphs produced by the autoencoder for various model settings are conducted using unstructured snapshot data sourced from large-eddy simulations in a backward-facing step (BFS) flow configuration with an OpenFOAM-based flow solver at high Reynolds numbers.

Syntax-based dynamic latent graph for event relation extraction

This paper focuses on extracting temporal and parent–child relationships between news events in social news. Previous methods have proved that syntactic features are valid. However, most previous methods directly use the static outcomes parsed by syntactic parsing tools, but task-irrelevant or erroneous parses will inevitably degrade the performance of the model. In addition, many implicit higher-order connections that are directly related and critical to tasks are not explicitly exploited. In this paper, we propose a novel syntax-based dynamic latent graph model (SDLG) for this task. Specifically, we first apply a syntactic type-enhanced attention mechanism to assign different weights to different connections in the parsing results, which helps to filter out noisy connections and better fuse the information in the syntactic structures. Next, we introduce a dynamic event pair-aware induction graph to mine the task-related latent connections. It constructs a potential attention matrix to complement and correct the supervised syntactic features, using the semantics of the event pairs as a guide. Finally, the latent graph, together with the syntactic information, is fed into the graph convolutional network to obtain an improved representation of the event to complete relational reasoning. We have conducted extensive experiments on four public benchmarks, MATRES, TCR, HiEve and TB-Dense. The results show that our model outperforms the state-of-the-art model by 0.4%, 1.5%, 3.0% and 1.3% in F1 scores on the four datasets, respectively. Finally, we provide detailed analyses to show the effectiveness of each proposed component.

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications.

Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Two prominent examples are molecule property prediction and brain connectome analysis. Importantly, recent works have shown that considering relationships between input data samples has a positive regularizing effect on the downstream task in healthcare applications. These relationships are naturally modeled by a (possibly unknown) graph structure between input samples. In this work, we propose Graph-in-Graph (GiG), a neural network architecture for protein classification and brain imaging applications that exploits the graph representation of the input data samples and their latent relation. We assume an initially unknown latent-graph structure between graph-valued input data and propose to learn a parametric model for message passing within and across input graph samples, end-to-end along with the latent structure connecting the input graphs. Further, we introduce a Node Degree Distribution Loss (NDDL) that regularizes the predicted latent relationships structure. This regularization can significantly improve the downstream task. Moreover, the obtained latent graph can represent patient population models or networks of molecule clusters, providing a level of interpretability and knowledge discovery in the input domain, which is of particular value in healthcare.

Graph convolution with topology refinement for Automatic Reinforcement Learning

Reinforcement learning faces the challenge of sparse rewards. Existing research utilizes reward shaping based on graph convolutional neural networks (GCNs) to address this challenge. However, the automatic construction of optimal graph has been a long standing issue. Here we propose Graph Convolution with Topology Refinement for Automatic Reinforcement Learning (GTR), based on the construction of new latent graph to replace the original input graph for more effective reward shaping. It is found from this work that, the most suitable state node can be extracted through the graph entropy. Subsequently we map the original graph to subset of nodes adaptively to form a new and more compact latent graph. Since GTR utilizes trainable projection vectors for projecting all node features into one-dimensional representation, the inter-connections between the nodes of the newly constructed latent graph are consistent with the original ones. The proposed GTR stems from mathematical grounds, and preliminary experiments have shown that the proposed GTR has considerable improvement on Atari benchmark and Mujoco benchmark. Further experiment and ablation analysis have given further supports to this work.

Consistent graph embedding network with optimal transport for incomplete multi-view clustering

Existing incomplete multi-view learning models focus on reconstructing the latent variables of multiple views by exploring complementary and consistent information among diverse views. However, filling the missing information for views results in a loss of consistency, while fusion and reconstruction between views face over-fitting problems. The optimal transport algorithm delicately measures the distance of two distributions, resulting in decreased reconstruction errors and guaranteeing consistency and complementarity across multiple views of the data. In light of this, this paper proposes the incorporation of the optimal transport algorithm into the framework of incomplete multi-view clustering. The proposed consistent graph embedding network (CGEN-OT) via optimal transport combines the adversarial module and fusion module to learn a completed latent graph embedding. Specifically, CGEN-OT utilizes an adversarial module to generate complete views and fuses them into a consistent embedding, and introduces reconstruction loss and Sinkhorn loss to jointly optimize the proposed network and obtain superior latent graph embedding and clustering performance. To further validate the clustering accuracy and convergence of the CGEN-OT, experimental evaluation was conducted on six distinct incomplete datasets. A comparison with existing state-of-the-art models highlights the superiority of the proposed framework.

Meta-path infomax joint structure enhancement for multiplex network representation learning

Network representation learning has achieved significant success in homogeneous network data analysis in recent years. Nevertheless, they cannot be directly applied in multiplex networks. To overcome the characteristic of heterogeneity in multiplex networks, several emerging methods utilize the concept of meta-path to denote different types of relations and obtain the node representations for each type of meta-path individually. Despite the remarkable progress, there still exist two important issues in the previous approaches. First, the complementary information between different types of meta-paths that may make the representations more discriminative, is rarely investigated. Second, current studies generally learn multiplex node representations based on the original graph structure, while overlooking the latent relations between nodes. To address the aforementioned issues, in this paper, we propose a novel model with Meta-path Infomax joint Structure Enhancement (MISE) for multiplex network representations. Specifically, we first develop a meta-path infomax mechanism, which maximizes the mutual information between local and global meta-path representations, making the node representation contain more complementary information. Additionally, we propose a graph structure learning module that captures the implicit correlations between nodes to construct the latent graph structure. Such structure enhancement is a simple yet surprisingly effective technique to learn high-quality representations. We sufficiently evaluate the performance of our proposal on both supervised and unsupervised downstream tasks. Comprehensive experimental results show that our MISE achieves a promising boost in performance on a variety of real-world datasets for multiplex network representation learning.