Tensor Graph Research Articles

Probabilistic power flow based on physics-guided graph neural networks

Under the high-dimensional and nonlinear stochastic power system environment, artificial intelligence (AI) is becoming a promising alternative to the urgent demand for probabilistic power flow (PPF). However, traditional AI only learns from experiences in data and is unable to satisfy physical constraints. This may result in an undesired infeasible inference for PPF. To solve this issue, a physics-guided graph neural network (PG-GNN)-based PPF analysis method is proposed. At the outset, alternating current power flow equation is analyzed to produce gradients for connecting physical component and AI. The proposed PG-GNN then incorporates the sensitivities into the training tensor graph such that it enables in-depth physical learning. At the same time, the GNN serves to enhance generalizability in varying topology. The well-trained PG-GNN is finally leveraged to surrogate traditional power flow solver in Monte-Carlo method, such that real-time PPF is realized. Numerical tests on benchmarks demonstrate that, in unseen scenarios, the proposed method enables only little gap versus the exact baseline, but beats other rivals with over tenfold computing efficiency. Moreover, comparisons with traditional AIs manifest that our method holds better generalizability.

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

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

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.

Distinct alterations in white matter properties and organization related to maternal treatment initiation in neonates exposed to HIV but uninfected

HIV exposed-uninfected (HEU) infants and children are at risk of developmental delays as compared to HIV uninfected unexposed (HUU) populations. The effects of exposure to in utero HIV and ART regimens on the HEU the developing brain are not well understood. In a cohort of 2-week-old newborns, we used diffusion tensor imaging (DTI) tractography and graph theory to examine the influence of HIV and ART exposure in utero on neonate white matter integrity and organisation. The cohort included HEU infants born to mothers who started ART before conception (HEUpre) and after conception (HEUpost), as well as HUU infants from the same community. We investigated HIV exposure and ART duration group differences in DTI metrics (fractional anisotropy (FA) and mean diffusivity (MD)) and graph measures across white matter. We found increased MD in white matter connections involving the thalamus and limbic system in the HEUpre group compared to HUU. We further identified reduced nodal efficiency in the basal ganglia. Within the HEUpost group, we observed reduced FA in cortical-subcortical and cerebellar connections as well as decreased transitivity in the hindbrain area compared to HUU. Overall, our analysis demonstrated distinct alterations in white matter integrity related to the timing of maternal ART initiation that influence regional brain network properties.

MM-EMOG: Multi-Label Emotion Graph Representation for Mental Health Classification on Social Media

More than 80% of people who commit suicide disclose their intention to do so on social media. The main information we can use in social media is user-generated posts, since personal information is not always available. Identifying all possible emotions in a single textual post is crucial to detecting the user’s mental state; however, human emotions are very complex, and a single text instance likely expresses multiple emotions. This paper proposes a new multi-label emotion graph representation for social media post-based mental health classification. We first construct a word–document graph tensor to describe emotion-based contextual representation using emotion lexicons. Then, it is trained by multi-label emotions and conducts a graph propagation for harmonising heterogeneous emotional information, and is applied to a textual graph mental health classification. We perform extensive experiments on three publicly available social media mental health classification datasets, and the results show clear improvements.

Robust Factorizations and Colorings of Tensor Graphs

Robust Factorizations and Colorings of Tensor Graphs

Deep graph tensor learning for temporal link prediction

Knowledge discovery on dynamic graphs has received much attention in recent years. As a key task of dynamic graph research, the goal of temporal link prediction is to accurately predict the time-varying links in dynamic networks. Uncertainty in link emergence is a major challenge in this research, as it is not easy to learn stable and reliable link-level feature representations, which are usually readily available on static graphs. In order to adapt to the ever-changing graph structure, this paper proposes to construct a deep graph tensor learning model, which can capture the contextual characteristics of graph evolution from both the graph structure (spatial) mode and the link sequence (temporal) mode. Therefore, compared to link prediction on static graphs, temporal link prediction can benefit more from the link-level embedding representations coupled with spatio-temporal features. The experimental results on seven public dynamic graph datasets show that the prediction accuracy obtained by the new model is overall better than competing models such as GC-LSTM, EvolveGCN, and HTGN. In the meantime, as a result of getting rid of the traditional RNN learning paradigm, the new model is also significantly better than the traditional temporal graph learning model in terms of training efficiency.

Hypercomplex Graph Neural Network: Towards Deep Intersection of Multi-modal Brain Networks.

The multi-modal neuroimage study has provided insights into understanding the heteromodal relationships between brain network organization and behavioral phenotypes. Integrating data from various modalities facilitates the characterization of the interplay among anatomical, functional, and physiological brain alterations or developments. Graph Neural Networks (GNNs) have recently become popular in analyzing and fusing multi-modal, graph-structured brain networks. However, effectively learning complementary representations from other modalities remains a significant challenge due to the sophisticated and heterogeneous inter-modal dependencies. Furthermore, most existing studies often focus on specific modalities (e.g., only fMRI and DTI), which limits their scalability to other types of brain networks. To overcome these limitations, we propose a HyperComplex Graph Neural Network (HC-GNN) that models multi-modal networks as hypercomplex tensor graphs. In our approach, HC-GNN is conceptualized as a dynamic spatial graph, where the attentively learned inter-modal associations are represented as the adjacency matrix. HC-GNN leverages hypercomplex operations for inter-modal intersections through cross-embedding and cross-aggregation, enriching the deep coupling of multi-modal representations. We conduct a statistical analysis on the saliency maps to associate disease biomarkers. Extensive experiments on three datasets demonstrate the superior classification performance of our method and its strong scalability to various types of modalities. Our work presents a powerful paradigm for the study of multi-modal brain networks.

Temporal Knowledge Extrapolation Based on Fine-grained Tensor Graph Attention Network for Responsible AI

Temporal Knowledge Extrapolation Based on Fine-grained Tensor Graph Attention Network for Responsible AI

Tensor‐based gated graph neural network for automatic vulnerability detection in source code

AbstractThe rapid expansion of smart devices leads to the increasing demand for vulnerability detection in the cyber security field. Writing secure source codes is crucial to protect applications and software. Recent vulnerability detection methods are mainly using machine learning and deep learning. However, there are still some challenges, how to learn accurate source code semantic embedding at the function level, how to effectively perform vulnerability detection using the learned semantic embedding of source code and how to solve the overfitting problem of learning‐based models. In this paper, we consider codes as various graphs with node features and propose a tensor‐based gated graph neural network called TensorGNN to produce code embedding for function‐level vulnerability detection. First, we propose a high‐dimensional tensor for combining different code graph representations. Second, inspired by the work of tensor technology, we propose the TensorGNN model to produce accurate code representations using the graph tensor. We evaluate our model on 7 C and C++ large open‐source code corpus (e.g. SARD&NVD, Debian, SATE IV, FFmpeg, libpng&LibTiff, Wireshark and Github datasets), which contains 13 types of vulnerabilities. Our TensorGNN model improves on existing state‐of‐the‐art works by 10%–30% on average in terms of vulnerability detection accuracy and F1, while our TensorGNN model needs less training time and model parameters. Specifically, compared with other existing works, our model reduces 25–47 times of the number of parameters and decreases 3–10 times of training time. Results of evaluations show that TensorGNN has better performance while using fewer training parameters and less training time.

Joint Multidimensional Pattern for Spectrum Prediction Using GNN.

In general, judging the use/idle state of the wireless spectrum is the foundation for cognitive radio users (secondary users, SUs) to access limited spectrum resources efficiently. Rich information can be mined by the inherent correlation of electromagnetic spectrum data from SUs in time, frequency, space, and other dimensions. Therefore, how to efficiently use the spectrum status of each SU implementation of reception multidimensional combination forecasting is the core of this paper. In this paper, we propose a deep-learning hybrid model called TensorGCN-LSTM based on the tensor data structure. The model treats SUs deployed at different spatial locations under the same frequency, and the spectrum status of SUs themselves under different frequencies in the task area as nodes and constructs two types of graph structures. Graph convolutional operations are used to sequentially extract corresponding spatial-domain and frequency-domain features from the two types of graph structures. Then, the long short-term memory (LSTM) model is used to fuse the spatial, frequency, and temporal features of the cognitive radio environment data. Finally, the prediction task of the spectrum distribution situation is accomplished through fully connected layers. Specifically, the model constructs a tensor graph based on the spatial similarity of SUs' locations and the frequency correlation between different frequency signals received by SUs, which describes the electromagnetic wave's dependency relationship in spatial and frequency domains. LSTM is used to capture the electromagnetic wave's dependency relationship in the temporal domain. To evaluate the effectiveness of the model, we conducted ablation experiments on LSTM, GCN, GC-LSTM, and TensorGCN-LSTM models using simulated data. The experimental results showed that our model achieves better prediction performance in RMSE, and the correlation coefficient R2 of 0.8753 also confirms the feasibility of the model.

MTGDC: A Multi-Scale Tensor Graph Diffusion Clustering for Single-Cell RNA Sequencing Data.

Single-cell RNA sequencing (scRNA-seq) is a new technology that focuses on the expression levels for each cell to study cell heterogeneity. Thus, new computational methods matching scRNA-seq are designed to detect cell types among various cell groups. Herein, we propose a Multi-scale Tensor Graph Diffusion Clustering (MTGDC) for single-cell RNA sequencing data. It has the following mechanisms: 1) To mine potential similarity distributions among cells, we design a multi-scale affinity learning method to construct a fully connected graph between cells; 2) For each affinity matrix, we propose an efficient tensor graph diffusion learning framework to learn high-order information among multi-scale affinity matrices. Firstly, the tensor graph is explicitly introduced to measure cell-cell edges with local high-order relationship information. To further preserve more global topology structure information in the tensor graph, MTGDC implicitly considers the propagation of information via a data diffusion process by designing a simple and efficient tensor graph diffusion update algorithm. 3) Finally, we mix together the multi-scale tensor graphs to obtain the fusion high-order affinity matrix and apply it to spectral clustering. Experiments and case studies showed that MTGDC had obvious advantages over the state-of-art algorithms in robustness, accuracy, visualization, and speed. MTGDC is available at https://github.com/lqmmring/MTGDC.

Unbalanced incomplete multi-view clustering based on low-rank tensor graph learning

Unbalanced incomplete multi-view clustering based on low-rank tensor graph learning

Cross-view Graph Matching Guided Anchor Alignment for Incomplete Multi-view Clustering

Multi-view bipartite graph clustering methods select a few representative anchors and then establish a connection with original samples to generate the bipartite graphs for clustering, which maintains impressive performance while reducing time and space complexities. Despite their effectiveness in large-scale applications, few of them focus on cross-view anchor misalignment (CAM) problem. Then, misaligned anchor sets could destroy the consistent graph semantic structure of bipartite graphs across different views, thus hindering subsequent graph fusion and degrading the clustering performance. Especially when it comes to incomplete data, solving CAM problem becomes an intractable challenge. To address this challenge, we propose a novel Cross-view Graph Matching guided Anchor Alignment (CGMAA) for incomplete multi-view bipartite clustering. Specifically, we first propose a novel CGMAA framework to address CAM problem by predefining an anchor graph according to the prior anchor information. In addition, we unify CGMAA and bipartite graph tensor learning for incomplete multi-view clustering. Extensive experiments on ten complete/incomplete benchmark datasets demonstrate the effectiveness, efficiency, and superiority of the proposed CGMAA framework.

Urban Knowledge Graph Aided Mobile User Profiling

Nowadays, the explosive growth of personalized web applications and the rapid development of artificial intelligence technology have flourished the recent research on mobile user profiling, i.e., inferring the user profile from mobile behavioral data. Particularly, existing studies mainly follow the data-driven paradigm to develop feature engineering and representation learning on such data, which however suffer from the robustness issue, i.e., generalizing poorly across datasets and profiles without considering semantic knowledge therein. In comparison, the rising knowledge-driven paradigm built upon the knowledge graph (KG) offers a potential solution to mitigate such weakness. Therefore, in this paper, we propose a Knowledge Graph aided framework for Mobile User Profiling (KG-MUP). Specifically, to distil semantic knowledge among data, we firstly construct an urban knowledge graph (UrbanKG) with domain entities like users, regions, point of interests (POIs), etc. identified, as well as semantic relations for home, workplace, spatiality, etc. extracted. Moreover, we leverage tensor decomposition and graph neural network to obtain knowledgeable user representations from UrbanKG. In addition, we introduce several customized features to quantify individual mobility characteristics for mobile user profiling. Extensive experiments on three real-world mobility datasets demonstrate that KG-MUP achieves state-of-the-art performance on user profile inference tasks. Moreover, further results also reveal the importance of various semantic knowledge to user profile inference, which provides meaningful insights on user modeling with mobile behavioral data.

Structural connectome alterations in anxious dogs: a DTI-based study

Anxiety and fear are dysfunctional behaviors commonly observed in domesticated dogs. Although dogs and humans share psychopathological similarities, little is known about how dysfunctional fear behaviors are represented in brain networks in dogs diagnosed with anxiety disorders. A combination of diffusion tensor imaging (DTI) and graph theory was used to investigate the underlying structural connections of dysfunctional anxiety in anxious dogs and compared with healthy dogs with normal behavior. The degree of anxiety was assessed using the Canine Behavioral Assessment & Research Questionnaire (C-BARQ), a widely used, validated questionnaire for abnormal behaviors in dogs. Anxious dogs showed significantly decreased clustering coefficient ({C}_{p}), decreased global efficiency ({E}_{glob}), and increased small-worldness (σ) when compared with healthy dogs. The nodal parameters that differed between the anxious dogs and healthy dogs were mainly located in the posterior part of the brain, including the occipital lobe, posterior cingulate gyrus, hippocampus, mesencephalon, and cerebellum. Furthermore, the nodal degree ({K}_{i}) of the left cerebellum was significantly negatively correlated with “excitability” in the C-BARQ of anxious dogs. These findings could contribute to the understanding of a disrupted brain structural connectome underlying the pathological mechanisms of anxiety-related disorders in dogs.

Auto-weighted multiple kernel tensor clustering

Multiple kernel subspace clustering (MKSC) has attracted intensive attention since its powerful capability of exploring consensus information by generating a high-quality affinity graph from multiple base kernels. However, the existing MKSC methods still exist the following limitations: (1) they essentially neglect the high-order correlations hidden in different base kernels; and (2) they perform candidate affinity graph learning and consensus affinity graph learning in two separate steps, where suboptimal solution may be obtained. To alleviate these problems, a novel MKSC method, namely auto-weighted multiple kernel tensor clustering (AMKTC), is proposed. Specifically, AMKTC first integrates the consensus affinity graph learning and candidate affinity graph learning into a unified framework, where the optimal goal can be achieved by making these two learning processes negotiate with each other. Further, an auto-weighted fusion scheme with one-step manner is proposed to learn the final consensus affinity graph, where the reasonable weights will be automatically learned for each candidate graph. Finally, the essential high-order correlations between multiple base kernels can be captured by leveraging tensor-singular value decomposition (t-SVD)-based tensor nuclear norm constraint on a 3-order graph tensor. Experiments on seven benchmark datasets with eleven comparison methods demonstrate that our method achieves state-of-the-art clustering performance.

Multi-View Tensor Graph Neural Networks Through Reinforced Aggregation

Graph Neural Networks (GNNs) have yielded fruitful results in learning multi-view graph data. However, it is challenging for existing GNNs to capture the potential correlation information (PCI) among the graph structure features of multiple views. It is also challenging to adaptively identify valuable neighbors for node feature fusion in different views. To this end, we propose a novel <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</u> einforced <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</u> ensor <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</u> raph <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</u> eural <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</u> etwork (RTGNN) framework to more effectively perform multi-view graph representation learning through reinforcing inter- and intra-graph aggregation. Specifically, RTGNN first uses tensor decomposition to extract the graph structure features (GSFs) of each view in the common feature space. These GSFs contain the PCI of multiple views and alleviate fusion conflicts that may be caused by differences between view feature spaces in cross-view feature fusion. Since fusing the features of all neighbor nodes may harm the features of the center node, we filter the irrelevant neighbors to improve the performance of intra-graph aggregation in each view. Concretely, a reinforcement learning (RL)-guided scheme is developed to automatically calculate the optimal filtering threshold for each view, avoiding tedious manual updates and infeasible back propagation updates. Experimental results and analysis on five datasets show that RTGNN surpasses the best multi-view graph representation baselines and achieves the maximum 14.26% performance improvement in terms of F1. The code link is <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/RingBDStack/RTGNN</uri> .

Drift Detection of Intelligent Sensor Networks Deployment Based on Graph Stream

The optimal deployment of sensor nodes can effectively improve the monitoring performance of the sensor network. The existing optimization deployment strategies focus on how to achieve the optimal coverage or the maximal monitoring efficiency of the sensor network deployment, and lack research on the issue of when a deployed sensor network need to update its deployment. Considering that the parameters of the monitored targets by sensor network will vary over time, making the deployment a certain degree of time drift characteristic. In this paper, we propose a deployment drift detection algorithm based on graph stream for intelligent sensor networks (ISNs) to investigate the optimization deployment update time of sensor nodes for more efficient targets monitoring. We utilize graph stream to represent the topology of sensor network at different timestamps, and propose a projection fusion clustering algorithm based on Structural Clustering Algorithm for Networks (SCAN) to construct the tensor graph summarization within a sliding time window. According to the contrast between the node-level and the graph-level queries of the summary graph in adjacent windows, we refer Hoeffding boundary and graph contrastive loss function as the criterion to judge the optimal update time of the sensor network deployment. Experiments on Intel_Lab_Data and CIMIS datasets demonstrate that our approach can effectively detect the update moment of the optimal deployment of sensor network.

Toward Interpretable Graph Tensor Convolution Neural Network for Code Semantics Embedding

Intelligent deep learning-based models have made significant progress for automated source code semantics embedding, and current research works mainly leverage natural language-based methods and graph-based methods. However, natural language-based methods do not capture the rich semantic structural information of source code, and graph-based methods do not utilize rich distant information of source code due to the high cost of message-passing steps. In this paper, we propose a novel interpretable model, called graph tensor convolution neural network (GTCN), to generate accurate code embedding, which is capable of comprehensively capturing the distant information of code sequences and rich code semantics structural information. Firstly, we propose to utilize a high-dimensional tensor to integrate various heterogeneous code graphs with node sequence features, such as control flow, data flow. Secondly, inspired by the current advantages of graph-based deep learning and efficient tensor computations, we propose a novel interpretable graph tensor convolution neural network for learning accurate code semantic embedding from the code graph tensor. Finally, we evaluate three popular applications on the GTCN model, variable misuse detection, source code prediction, and vulnerability detection. Compared with current state-of-the-art methods, our model achieves higher scores with respect to the top-1 accuracy while costing less training time.