Similarity Graph Research Articles

Enhanced multi-scale networks for semantic segmentation

Multi-scale representation provides an effective answer to the scale variation of objects and entities in semantic segmentation. The ability to capture long-range pixel dependency facilitates semantic segmentation. In addition, semantic segmentation necessitates the effective use of pixel-to-pixel similarity in the channel direction to enhance pixel areas. By reviewing the characteristics of earlier successful segmentation models, we discover a number of crucial elements that enhance segmentation model performance, including a robust encoder structure, multi-scale interactions, attention mechanisms, and a robust decoder structure. The attention mechanism of the asymmetric non-local neural network (ANNet) is merged with multi-scale pyramidal modules to accelerate model segmentation while maintaining high accuracy. However, ANNet does not account for the similarity between pixels in the feature map channel direction, making the segmentation accuracy unsatisfactory. As a result, we propose EMSNet, a straightforward convolutional network architecture for semantic segmentation that consists of Integration of enhanced regional module (IERM) and Multi-scale convolution module (MSCM). The IERM module generates weights using four or five-stage feature maps, then fuses the input features with the weights and uses more computation. The similarity of the channel direction feature graphs is also calculated using ANNet’s auxiliary loss function. The MSCM module can more accurately describe the interactions between various channels, capture the interdependencies between feature pixels, and capture the multi-scale context. Experiments prove that we perform well in tests using the benchmark dataset. On Cityscapes test data, we get 82.2% segmentation accuracy. The mIoU in the ADE20k and Pascal VOC datasets are, respectively, 45.58% and 85.46%.

Relationship between brain structural network integrity and emotional symptoms in youth with perinatally-acquired HIV

Perinatally acquired HIV infection (PHIV) currently affects approximately 1.7 million children worldwide. Youth with PHIV (YPHIV) are at increased risk for emotional and behavioral symptoms, yet few studies have examined relationships between these symptoms and brain structure. Previous neuroimaging studies in YPHIV report alterations within the salience network (SN), cognitive control network (CCN), and default mode network (DMN). These areas have been associated with social and emotional processing, emotion regulation, and executive function. We examined structural brain network integrity from MRI using morphometric similarity networks and graph theoretical measures of segregation (transitivity), resilience (assortativity), and integration (global efficiency). We examined brain network integrity of 40 YPHIV compared to 214 youths without HIV exposure or infection. Amongst YPHIV, we related structural brain network metrics to the Emotional Symptoms Index of the Behavioral Assessment System for Children, 2nd edition. We also examined the relationship of inflammatory biomarkers in YPHIV to brain network integrity. YPHIV had significantly lower global efficiency in the SN, DMN, and the whole brain network compared to controls. YPHIV also demonstrated lower assortativity or resilience (i.e., network robustness) compared to controls in the DMN and whole brain network. Further, higher emotional symptom score was associated with higher global efficiency in the SN and lower global efficiency in the DMN, signaling more emotional challenges. A significant association was also found between several inflammatory and cardiac markers with structural network integrity. These findings suggest an impact of HIV on developing brain networks, and potential dysfunction of the SN and DMN in relation to network efficiency.

Knowledge-Aware Graph Self-Supervised Learning for Recommendation

Collaborative filtering (CF) based on graph neural networks (GNN) can capture higher-order relationships between nodes, which in turn improves recommendation performance. Although effective, GNN-based methods still face the challenges of sparsity and noise in real scenarios. In recent years, researchers have introduced graph self-supervised learning (SSL) techniques into CF to alleviate the sparse supervision problem. The technique first augments the data to obtain contrastive views and then utilizes the mutual information maximization to provide self-supervised signals for the contrastive views. However, the existing approaches based on graph self-supervised signals still face the following challenges: (i) Most of the works fail to effectively mine and exploit the supervised information from the item knowledge graph, resulting in suboptimal performance. (ii) Existing data augmentation methods are unable to fully exploit the potential of contrastive learning, because they primarily focus on the contrastive view of data structure changes and neglect the adjacent relationship among users and items. To address these issues, we propose a novel self-supervised learning approach, namely Knowledge-aware Graph Self-supervised Learning (KGSL). Specifically, we calculate node similarity based on semantic relations between items in the knowledge graph to generate a semantic-based item similarity graph. Then, the self-supervised learning contrast views are generated from both the user–item interaction graph and the item similarity graph, respectively. Maximization of the information from these contrastive views provides additional self-supervised signals to enhance the node representation capacity. Finally, we establish a joint training strategy for the self-supervised learning task and the recommendation task to further optimize the learning process of KGSL. Extensive comparative experiments as well as ablation experiments are conducted on three real-world datasets to verify the effectiveness of KGSL.

Possibilistic Neighborhood Graph: A New Concept of Similarity Graph Learning

Adaptive graph-based representation and learning methods have received extensive attention due to their good performance in supervised and unsupervised learning tasks. These methods often involve probability constraint, i.e., the sum-to-one constraint, when learning a similarity graph. Whereas this constraint may degrade the ability to precisely measure the similarity between samples. In terms of clustering tasks, limited by the sum-to-one constraint, the similarity between some noisy points may tend to be large, which causes these abnormal points to be grouped into a separate cluster, and other close clusters with normal points are merged. To address this problem, this study proposes a novel notion of possibilistic neighbor graph (PNG). In PNG, the possibility of two samples being neighbors can be measured adaptively and precisely by removing the sum-to-one constraint and incorporating a new regularization term. By using the possibility rather than the probability in the similarity graph learning, the solution space is enlarged without increasing the complexity. The mathematical properties of PNG are discussed in detail, and a new graph-based clustering method (CPNG) is also developed based on the learned PNG. Extensive experimental results on several benchmark datasets demonstrate the superiority of CPNG in comparison with some state-of-the-art methods.

ReeBundle: A Method for Topological Modeling of White Matter Pathways Using Diffusion MRI.

Tractography can generate millions of complex curvilinear fibers (streamlines) in 3D that exhibit the geometry of white matter pathways in the brain. Common approaches to analyzing white matter connectivity are based on adjacency matrices that quantify connection strength but do not account for any topological information. A critical element in neurological and developmental disorders is the topological deterioration and irregularities in streamlines. In this paper, we propose a novel Reeb graph-based method "ReeBundle" that efficiently encodes the topology and geometry of white matter fibers. Given the trajectories of neuronal fiber pathways (neuroanatomical bundle), we re-bundle the streamlines by modeling their spatial evolution to capture geometrically significant events (akin to a fingerprint). ReeBundle parameters control the granularity of the model and handle the presence of improbable streamlines commonly produced by tractography. Further, we propose a new Reeb graph-based distance metric that quantifies topological differences for automated quality control and bundle comparison. We show the practical usage of our method using two datasets: (1) For International Society for Magnetic Resonance in Medicine (ISMRM) dataset, ReeBundle handles the morphology of the white matter tract configurations due to branching and local ambiguities in complicated bundle tracts like anterior and posterior commissures; (2) For the longitudinal repeated measures in the Cognitive Resilience and Sleep History (CRASH) dataset, repeated scans of a given subject acquired weeks apart lead to provably similar Reeb graphs that differ significantly from other subjects, thus highlighting ReeBundle's potential for clinical fingerprinting of brain regions.

Multiview Data Clustering with Similarity Graph Learning Guided Unsupervised Feature Selection.

In multiview data clustering, consistent or complementary information in the multiview data can achieve better clustering results. However, the high dimensions, lack of labeling, and redundancy of multiview data certainly affect the clustering effect, posing a challenge to multiview clustering. A clustering algorithm based on multiview feature selection clustering (MFSC), which combines similarity graph learning and unsupervised feature selection, is designed in this study. During the MFSC implementation, local manifold regularization is integrated into similarity graph learning, with the clustering label of similarity graph learning as the standard for unsupervised feature selection. MFSC can retain the characteristics of the clustering label on the premise of maintaining the manifold structure of multiview data. The algorithm is systematically evaluated using benchmark multiview and simulated data. The clustering experiment results prove that the MFSC algorithm is more effective than the traditional algorithm.

An exploration of knowledge-organizing technologies to advance transdisciplinary back pain research.

Chronic low back pain (LBP) is influenced by a broad spectrum of patient-specific factors as codified in domains of the biopsychosocial model (BSM). Operationalizing the BSM into research and clinical care is challenging because most investigators work in silos that concentrate on only one or two BSM domains. Furthermore, the expanding, multidisciplinary nature of BSM research creates practical limitations as to how individual investigators integrate current data into their processes of generating impactful hypotheses. The rapidly advancing field of artificial intelligence (AI) is providing new tools for organizing knowledge, but the practical aspects for how AI may advance LBP research and clinical are beginning to be explored. The goals of the work presented here are to: (1) explore the current capabilities of knowledge integration technologies (large language models (LLM), similarity graphs (SGs), and knowledge graphs (KGs)) to synthesize biomedical literature and depict multimodal relationships reflected in the BSM, and; (2) highlight limitations, implementation details, and future areas of research to improve performance. We demonstrate preliminary evidence that LLMs, like GPT-3, may be useful in helping scientists analyze and distinguish cLBP publications across multiple BSM domains and determine the degree to which the literature supports or contradicts emergent hypotheses. We show that SG representations and KGs enable exploring LBP's literature in novel ways, possibly providing, trans-disciplinary perspectives or insights that are currently difficult, if not infeasible to achieve. The SG approach is automated, simple, and inexpensive to execute, and thereby may be useful for early-phase literature and narrative explorations beyond one's areas of expertise. Likewise, we show that KGs can be constructed using automated pipelines, queried to provide semantic information, and analyzed to explore trans-domain linkages. The examples presented support the feasibility for LBP-tailored AI protocols to organize knowledge and support developing and refining trans-domain hypotheses.

Discriminative multi-label feature selection with adaptive graph diffusion

Feature selection can alleviate the problem of the curse of dimensionality by selecting more discriminative features, which plays an important role in multi-label learning. Recently, embedded feature selection methods have received increasing attentions. However, most existing methods learn the low-dimensional embeddings under the guidance of the local structure between the original instance pairs, thereby ignoring the high-order structure between instances and being sensitive to noise in the original features. To address these issues, we propose a feature selection method named discriminative multi-label feature selection with adaptive graph diffusion (MFS-AGD). Specifically, we first construct a graph embedding learning framework equipped with adaptive graph diffusion to uncover a latent subspace that preserves the higher-order structure information between four tuples. Then, the Hilbert–Schmidt independence criterion (HSIC) is incorporated into the embedding learning framework to ensure the maximum dependency between the latent representation and labels. Benefiting from the interactive optimization of the feature selection matrix, latent representation and similarity graph, the selected features can accurately explore the higher-order structural and supervised information of data. By further considering the correlation between labels, MFS-AG is extended to a more discriminative version,i.e., LMFS-AG. Extensive experimental results on various benchmark data sets validate the advantages of the proposed MFS-AGD and LMFS-AGD methods.

Drug-disease association prediction using semantic graph and function similarity representation learning over heterogeneous information networks

Discovering new indications for existing drugs is a promising development strategy at various stages of drug research and development. However, most of them complete their tasks by constructing a variety of heterogeneous networks without considering available higher-order connectivity patterns in heterogeneous biological information networks, which are believed to be useful for improving the accuracy of new drug discovering. To this end, we propose a computational-based model, called SFRLDDA, for drug-disease association prediction by using semantic graph and function similarity representation learning. Specifically, SFRLDDA first integrates a heterogeneous information network (HIN) by drug-disease, drug-protein, protein-disease associations, and their biological knowledge. Second, different representation learning strategies are applied to obtain the feature representations of drugs and diseases from different perspectives over semantic graph and function similarity graphs constructed, respectively. At last, a Random Forest classifier is incorporated by SFRLDDA to discover potential drug-disease associations (DDAs). Experimental results demonstrate that SFRLDDA yields a best performance when compared with other state-of-the-art models on three benchmark datasets. Moreover, case studies also indicate that the simultaneous consideration of semantic graph and function similarity of drugs and diseases in the HIN allows SFRLDDA to precisely predict DDAs in a more comprehensive manner.

Multi-view clustering using a flexible and optimal multi-graph fusion method

Recently, many multi-view clustering (MVC) methods based on graphs have been proposed to address prevalent multi-view data. For these methods, the multi-graph fusion step, aim of which is to obtain a consensus graph is vital for obtaining good clustering performance. However, these methods still have two problems. First, the column sum of the consensus graph is restricted to one, which is not flexible enough for practical applications. Affected by the sum-to-one constraint, the similarity between some noisy points may be large, which may cause these abnormal points to be grouped into a separate cluster. Second, the cluster structure of the consensus graph is often not considered. To address these problems, in this paper, we propose a novel multi-view clustering using a flexible and optimal multi-graph fusion method (MVC/FOMF). Specifically, we first obtain the similarity graph of each view by using red the self-expressive method. Second, we fuse these graphs into a consensus graph whose column sum is constrained to s(0<s≤1), and we can adjust s to look for the best clustering performance. Third, we impose a rank constraint on the Laplacian matrix of the consensus graph to learn the best clustering structure. Finally, all these steps are unified into a framework and the corresponding optimization procedure, which is based on the alternating multiplier method, is also designed. More importantly, the complexity of our algorithm is also lower than those of many representative algorithms. Compared with that of the state-of-the-art algorithms, our algorithm shows very encouraging performance on some datasets. The code can be found at https://github.com/wulala2233/MVCFOMF.

Research on Traffic Flow Forecasting Based on Dynamic Spatial-Temporal Transformer

Accurate traffic flow forecasting is crucial for urban traffic control and route planning. Aiming at the difficulty in capturing dynamic spatio-temporal complexity of traffic flow, a dynamic spatio-temporal transformer (DST-Trans) model capable of modeling dynamic correlation of traffic flow is proposed, which consists of gated temporal convolutional network (GTCN), graph convolutional network (GCN), and spatio-temporal transformer (ST-TF). GTCN and GCN are utilized to capture the temporal and spatial characteristics of traffic flow, respectively. ST-TF includes a temporal transformer using temporal gated convolution and temporal multi-head self-attention to capture short-long term temporal features, and spatial transformer using spatial gated graph convolution and spatial multi-head self-attention to capture local-global dynamic spatial features. In addition, to take full advantage of the dynamic and static associations of road networks, multi-graph models of road relationship graph, similarity graph, and adaptive dynamic graph with SGGC are constructed. Experimental results show that the DST-Trans model in this paper shows good prediction performance in short-term (15 min), medium-term (30 min), and long-term (60 min) prediction, outperforming existing state-of-the-art models by up to approximately 7%.

Rough Set Techniques in Wireless Sensor Networks using Membership Function and Rough Labelling Graphs for Energy Aware Routing

Rough set theory and rough graphs are employed for data analysis. Rough graphs utilize approximations, and this paper presents a method for implementing rough graphs using rough membership functions and graph labeling for data structures and reduction. This paper proposes a rough graph labeling method, termed rough -labeling similarity graph, that utilizes a similarity measure for vertex and edge labeling. This method aims to minimize boundary regions in rough graphs and is applicable to wireless sensor networks (WSNs). In WSN, the proposed algorithms such as PSO-LSTM, COA-LSTM, LOA-LSTM integrates with rough set theory based rough -labeling for boundary region identification. The proposed method incorporates the membership functions encapsulates the rough labeling graphs for cluster boundary region identification for WSN. The cluster boundary for WSN is based on rough set membership and rough labelling is termed as rough set membership boundary region (RMB). RMB in WSN and implementation of proposed routing algorithm such as LOA-LSTM provides high throughput and energy saving when compared to existing cluster boundary structure methods such as Voronoi, Spectrum and Chain.

Global Ontology Entities Embeddings

Ontologies are among the most widely used types of knowledge representation formalisms. The application of deep learning techniques in the field of ontology engineering has reinforced the need to learn and generate representations of ontological data. This allows ontologies to be exploited by such models, and thus automate various ontology engineering tasks, where most of the existing tools and machine learning approaches require a numerical feature vectors associated with each concept. This paper outlines a novel approach for learning global ontology entities embeddings by exploiting the structure and the various taxonomic and semantic relationships present in ontologies, taking into account all the information present in the ontological graph and carried by the OWL/RDF triples. Thus, producing global ontology entities embeddings capturing the global ontological graph semantics and similarities enclosed in the source ontology. Three different neural network models have been proposed based on two architectures: multi-input and multi-output, trained using the contrastive estimation technique. The evaluation on OWL/RDF ontologies and word semantic similarity tasks using various graph and WordNet based similarity measures, show that our approach yields competitive results outperforming the state-of-the-art ontology and word embedding models.

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

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

Graph similarity learning for change-point detection in dynamic networks

Dynamic networks are ubiquitous for modelling sequential graph-structured data, e.g., brain connectivity, population migrations, and social networks. In this work, we consider the discrete-time framework of dynamic networks and aim at detecting change-points, i.e., abrupt changes in the structure or attributes of the graph snapshots. This task is often termed network change-point detection and has numerous applications, such as market phase discovery, fraud detection, and activity monitoring. In this work, we propose a data-driven method that can adapt to the specific network domain, and be used to detect distribution changes with no delay and in an online setting. Our algorithm is based on a siamese graph neural network, designed to learn a graph similarity function on the graph snapshots from the temporal network sequence. Without any prior knowledge on the network generative distribution and the type of change-points, our learnt similarity function allows to more effectively compare the current graph and its recent history, compared to standard graph distances or kernels. Moreover, our method can be applied to a large variety of network data, e.g., networks with edge weights or node attributes. We test our method on synthetic and real-world dynamic network data, and demonstrate that it is able to perform online network change-point detection in diverse settings. Besides, we show that it requires a shorter data history to detect changes than most existing state-of-the-art baselines.

Short-long temporal graph convolution network for grade monitoring in a first zinc rougher

With the rapid development of image-processing technology and neural networks, machine vision systems are being extensively used to monitor pulp grades in the froth flotation process. Specifically, an increasing number of researchers are obtaining temporal information from videos to monitor pulp grades. However, the relationship between the visual features of each video frame has not been sufficiently mined from a temporal perspective. To overcome this limitation, a short-long temporal graph convolution network (SLTGCN) trained with multiple froth videos is proposed herein to monitor the tailings grade of the first rougher layer in a zinc flotation circuit. First, the visual features of each video frame and the similarity graphs of images are treated as the nodes and edges of a graph, respectively. Thus, each froth video corresponds to a graph. Then, multiple graphs representing multiple froth videos are sent to a graph convolutional network (GCN) to predict the tailings grade. In particular, a temporal synchronous auxiliary network is proposed to ensure that the similarity graphs are consistent with the hidden features. The proposed model makes full use of the temporal information of froth videos and of the image frames in a froth video. The experimental results demonstrated the effectiveness of the proposed model. The root mean square error of the proposed model was at least 13.84% lower and its R-squared score was at least 8.62% greater than those of existing grade monitoring methods.

Similarity and Complementarity Attention-Based Graph Neural Networks for Mashup-Oriented Cloud API Recommendation

Mashups, which combine various web application programming interfaces (APIs) to implement some complex requirements, have grown to be a popular technique for developing service-oriented software. However, recommending suitable cloud APIs for mashup creation is challenging due to the rapidly increasing number of comparable APIs. Many existing mashup-oriented cloud API recommendations focus on functional similarity and ignore functional complementarity, which significantly impacts the accuracy of the recommendation results. Therefore, this paper proposed a feature representation and recommendation method for cloud APIs that fuses both similarity and complementarity. A heterogeneous information network of the cloud API ecosystem was constructed, and the neighbors, based on metapaths, were aggregated using a self-attention mechanism to generate the features of similarity and complementarity for the cloud APIs. Then, the mashup-related attention was utilized to fuse the two features, taking into consideration the varying preferences of different mashups towards similarity and complementarity features of cloud APIs. This fusion resulted in features that align cloud APIs with mashup requirements, which were employed to predict the probability of the mashup invoking a particular candidate cloud API. The proposed method was evaluated on a real dataset, and the results showed that it outperforms the baseline method and enhances the performance of mashup-oriented cloud API recommendations.

Analyzing complex networks: Extracting key characteristics and measuring structural similarities

SummaryThis paper discusses the importance of feature extraction and structure similarity measurement in the analysis of complex networks. Social networks, biological systems, and transportation networks are just a few examples of the many phenomena that have been modeled using complex networks. However, analyzing these networks can be challenging due to their large size and complexity. Feature extraction techniques can help to simplify the network by identifying key nodes or substructures. Structure similarity measurement techniques can be used to compare different networks and identify similarities and differences between them. Previous research has suggested that real‐world complex networks are influenced by multiplex features and either local or global features. However, the interaction between these characteristics is not well understood. The proposed approach outperforms other graph similarity methods on publicly available datasets, with accurate estimations of overall complex network structures. Specifically, the approach based on cosine similarity outperforms as compared to existing methods. Overall, this study highlights the importance of considering various graph features–local and global features and their interactions in the analysis of complex networks.

Spatiotemporal multi-graph convolutional network-based provincial-day-level terrorism risk prediction.

Predicting terrorism risk is crucial for formulating detailed counter-strategies. However, this task is challenging mainly because the risk of the concerned potential victim is not isolated. Terrorism risk has a spatiotemporal interprovincial contagious characteristic. The risk diffusion mechanism comes from three possibilities: cross-provincial terrorist attacks, internal and external echoes, and internal self-excitation. This study proposed a novel spatiotemporal graph convolutional network (STGCN)-based extension method to capture the complex and multidimensional non-Euclidean relationships between different provinces and forecast the daily risks. Specifically, three graph structures were constructed to represent the contagious process between provinces: the distance graph, the province-level root cause similarity graph, and the self-excited graph. The long short-term memory and self-attention layers were extended to STGCN for capturing context-dependent temporal characters. At the same time, the one-dimensional convolutional neural network kernel with the gated linear unit inside the classical STGCN can model single-node-dependent temporal features, and the spectral graph convolution modules can capture spatial features. The experimental results on Afghanistan terrorist attack data from 2005 to 2020 demonstrate the effectiveness of the proposed extended STGCN method compared to other machine learning prediction models. Furthermore, the results illustrate the crucial of capturing comprehensive spatiotemporal correlation characters among provinces. Based on this, this article provides counter-terrorism management insights on addressing the long-term root causes of terrorism risk and performing short-term situational prevention.

DeepSIM: a novel deep learning method for graph similarity computation

Graphs are widely used to model real-life information, where graph similarity computation is one of the most significant applications, such as inferring the properties of a compound based on similarity to a known group. Definition methods (e.g., graph edit distance and maximum common subgraph) have extremely high computational cost, and the existing efficient deep learning methods suffer from the problem of inadequate feature extraction which would have a bad effect on similarity computation. In this paper, a double-branch model called DeepSIM was raised to deeply mine graph-level and node-level features to address the above problems. On the graph-level branch, a novel embedding relational reasoning network was presented to obtain interaction between pairwise inputs. Meanwhile, a new local-to-global attention mechanism is designed to improve the capability of CNN-based node-level feature extraction module on another path. In DeepSIM, double-branch outputs will be concatenated as the final feature. The experimental results demonstrate that our methods perform well on several datasets compared to the state-of-the-art deep learning models in related fields.Graphical abstract