Joint Graph Research Articles

Multiple network embedding for anomaly detection in time series of graphs

The problem of anomaly detection in time series of graphs is considered, focusing on two related inference tasks: the detection of anomalous graphs within a time series and the detection of temporally anomalous vertices. These tasks are approached via the adaptation of multiple adjacency spectral embedding (MASE), a statistically principled method for joint graph inference. The effectiveness of the method is demonstrated for these inference tasks, and its performance is assessed based on the nature of detectable anomalies. Theoretical justification is provided, along with insights into its use. The approach identifies anomalous vertices beyond just large degree changes when applied to the Enron communication graph, a large-scale commercial search engine time series, and a larval Drosophila connectome.

Pairwise Intent Graph Embedding Learning for Context-Aware Recommendation with Knowledge Graph

Different from the data sparsity that traditional recommendations suffer from, context-aware recommender systems (CARS) face specific sparsity challenges related to contextual features, i.e., feature sparsity and interaction sparsity. How knowledge graphs address these challenges remains under-discussed. To bridge this gap, in this paper, we first propose a novel pairwise intent graph (PIG) containing nodes of users, items, entities, and enhanced intents to integrate knowledge graphs into CARS efficiently. Enhanced intent nodes are generated through the specific fusion of relational sub-intent and contextual sub-intent, and they are derived from semantic information and contextual information, respectively. We develop a pairwise intent graph embedding learning (PING) framework based on it. Specifically, our PING uses a pairwise intent joint graph convolution module to obtain refined embedding of all the features, where each enhanced intent node acts as a hub to effectively propagate information among different features and between all the features and knowledge graphs. Then, a recommendation module with refined embeddings is used to replace the randomly initialized embeddings of downstream recommendation models to improve model performance. Extensive experiments on three public datasets and some real-world scenarios verify the effectiveness and compatibility of our PING.

Sparse sampling photoacoustic reconstruction with a graph regularization group sparse dictionary

Photoacoustic tomography (PAT) has emerged as a promising biomedical imaging technique. The combination of optical contrast and ultrasound spatial resolution in photoacoustic tomography overcomes the limitations of optical scattering, enabling clear imaging of tissue structures. However, achieving high-resolution photoacoustic images typically requires a large number of sensor detection elements for sufficient angular coverage. This demand for extensive data acquisition and processing raises concerns about efficiency and system complexity. While sparse sampling strategies can improve efficiency, preserving detailed structural information becomes challenging with a minimal number of detectors. To address the challenges of sparse sampling, compressed sensing (CS) techniques have been successfully applied for image reconstructions in 2D and 3D photoacoustic embodiments. In this context, we propose a joint graph regularization group sparse dictionary and total variational regularization (GRGS-TV) algorithm based on our previous work of a group sparse dictionary. It preserves structured information and geometric relationships among dictionary atoms. Moreover, TV regularization effectively preserves edge structures while exhibiting a certain degree of robustness and flexibility. Numerical simulations and in vivo experiments on mice validate the effectiveness of this method in improving photoacoustic image quality and suppressing artifacts. Comparative evaluations against other algorithms show enhanced performance in terms of image reconstruction evaluation indices. This innovative approach holds promise for advancing photoacoustic imaging in biomedical research and clinical diagnostics.

Complex system anomaly detection via learnable temporal-spatial graph with degradation tendency segmentation

To guarantee the safety and reliability of equipment operation, such as liquid rocket engine (LRE), carrying out system-level anomaly detection (AD) is crucial. However, current methods ignore the prior knowledge of mechanical system itself, and seldom unite the observations with the inherent relation in data tightly. Meanwhile, they neglect the weakness and nonindependence of system-level anomaly which is different from component fault. To overcome above limitations, we propose a separate reconstruction framework using worsened tendency for system-level AD. To prevent anomalous feature being attenuated, we first propose to divide single sample into two equal-length parts along the temporal dimension. And we maximize the mean maximum discrepancy (MMD) between feature segments to force encoders to learn normal features with different distributions. Then, to fully explore the multivariate time series, we model temporal-spatial dependence by temporal convolution and graph attention. Besides, a joint graph learning strategy is proposed to handle prior knowledge and data characteristics simultaneously. Finally, the proposed method is evaluated on two real multi-sensor datasets from LRE and the results demonstrate the effectiveness and potential of the proposed method on system-level AD.

Containment control of systems with constraints and bounded disturbances

AbstractThis article studies the distributed containment control of a second‐order discrete‐time multi‐agent system with convex constraints on positions, nonconvex constraints on velocities, bounded disturbances on static points and switching topologies. A distributed control algorithm with disturbance information and local information is proposed. It is proved that when the static points with disturbances and the joint graph have a directed spanning forest among each time interval, all agents are gradually driven to the neighborhood of a convex hull spanned by the static points, and an upper bound of the neighborhood is obtained. The most innovative point is to utilize a rigorous mathematical theory to deal with convex constraint error rather than a geometric explanation. Meanwhile, another control algorithm with static point information and local information is proposed to converge all agents to the convex hull in the absence of external disturbances. Additionally, a numerical example is conducted to illustrate this theory.

TransGCN: a semi-supervised graph convolution network-based framework to infer protein translocations in spatio-temporal proteomics.

Protein subcellular localization (PSL) is very important in order to understand its functions, and its movement between subcellular niches within cells plays fundamental roles in biological process regulation. Mass spectrometry-based spatio-temporal proteomics technologies can help provide new insights of protein translocation, but bring the challenge in identifying reliable protein translocation events due to the noise interference and insufficient data mining. We propose a semi-supervised graph convolution network (GCN)-based framework termed TransGCN that infers protein translocation events from spatio-temporal proteomics. Based on expanded multiple distance features and joint graph representations of proteins, TransGCN utilizes the semi-supervised GCN to enable effective knowledge transfer from proteins with known PSLs for predicting protein localization and translocation. Our results demonstrate that TransGCN outperforms current state-of-the-art methods in identifying protein translocations, especially in coping with batch effects. It also exhibited excellent predictive accuracy in PSL prediction. TransGCN is freely available on GitHub at https://github.com/XuejiangGuo/TransGCN.

MotionRender: A simple Python implementation of video motion visualization for 3D motion capture data

We describe a Python library project for generating animations of simple 3D motion capture data points. The motion capture method is agnostic with respect to this visualizaiton tool, expecting a time series of time stamped coordinates captured in a 3-dimensional space. One of the advantages of this tool is the simple data format design. This tool was developed originally for a Kinect system implementing skeleton tracking of 15 joint positions, where each data point consists of an accurate time of capture (time stamp), and 3 accurate coordinate (x, y, z) positions of each of the 15 joints at each time step. In addition to the motion capture time series, all that is needed is a joint graph file describing the relationship of the joint edges to one another. This library can be extended to visualize and create animations of motion capture data that can be reformulated using this basic structure of a time series of time stamped 3D coordinates and a joint graph description file. This library should be useful as is, or with easy modification, for many such visualization requirements of similar motion capture data.

Robust Joint Graph learning for Multi-view Clustering

Robust Joint Graph learning for Multi-view Clustering

Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting

Recent studies have shifted their focus towards formulating traffic forecasting as a spatio-temporal graph modeling problem. Typically, they constructed a static spatial graph at each time step and then connected each node with itself between adjacent time steps to create a spatio-temporal graph. However, this approach failed to explicitly reflect the correlations between different nodes at different time steps, thus limiting the learning capability of graph neural networks. Additionally, those models overlooked the dynamic spatio-temporal correlations among nodes by using the same adjacency matrix across different time steps. To address these limitations, we propose a novel approach called Spatio-Temporal Joint Graph Convolutional Networks (STJGCN) for accurate traffic forecasting on road networks over multiple future time steps. Specifically, our method encompasses the construction of both pre-defined and adaptive spatio-temporal joint graphs (STJGs) between any two time steps, which represent comprehensive and dynamic spatio-temporal correlations. We further introduce dilated causal spatio-temporal joint graph convolution layers on the STJG to capture spatio-temporal dependencies from distinct perspectives with multiple ranges. To aggregate information from different ranges, we propose a multi-range attention mechanism. Finally, we evaluate our approach on five public traffic datasets and experimental results demonstrate that STJGCN is not only computationally efficient but also outperforms 11 state-of-the-art baseline methods.

Sample-weighted fused graph-based semi-supervised learning on multi-view data

Research in semi-supervised learning on graphs has attracted more and more attention in recent years, as learning on graphs is applied in more and more domains and labeling data is expensive and time-consuming. Some scenarios have inherent graph structures in their data, such as the relationships between people in social scenarios or the relationships between objects that are mutually referenced. However, there are also many data types without inherent graph structures, such as image data, and each image can be described with different features, which is a typical type of multi-view data. For image data and other non-graph data, there are significantly fewer deep learning approaches that target multi-view graph-based semi-supervised learning. This paper attempts to fill this gap. Based on the Graph Convolutional Network (GCN) architecture, we propose a Sample-weighted Fused Graph-based Semi-supervised Classification (WFGSC) method for multi-view data in this paper. It (i) constructs a semi-supervised graph in each view using a flexible model for joint graph and label estimation, (ii) obtains an additional graph based on the representation of nodes provided by the joint estimator, and then obtains a fused graph between all views, (iii) gives higher weights to hard-to-classify samples, (iv) proposes a loss function to train the GCN on the fused features and the consensus graph that integrates graph auto-encoder loss and label smoothing over the consensus graph. The results of our experiments on six multi-view datasets show that our WFGSC performs well on both fused graph construction and semi-supervised classification, and generally outperforms traditional GCNs and other multi-view semi-supervised multi-view classification methods.11Source code: https://github.com/BiJingjun/WFGSC.

JGSED: An End-to-End Spectral Clustering Model for Joint Graph Construction, Spectral Embedding and Discretization

Most of the existing graph-based clustering models performed clustering by adopting a two-stage strategy which first completes the spectral embedding from a given fixed graph and then resorts to other clustering methods such as <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$k$</tex-math></inline-formula> means to achieve discrete cluster results. On one hand, such a discretization operation easily causes that the obtained results deviate far from the true solution. On the other hand, clustering performance heavily relies on the quality of graph; therefore, the fixed graph is usually not optimal enough. In addition, clustering by separated steps inevitably breaks the underlying connections among the graph construction, spectral embedding and discretization. To address these drawbacks, in this paper, we propose a new spectral clustering model termed JGSED which integrates the graph construction, spectral embedding and spectral rotation together into a unified objective. JGSED is an end-to-end framework to directly take data as input and output the final binary cluster indicator matrix. An efficient algorithm is proposed to optimize the model variables in JGSED, which can be co-evolved towards the optimum. Extensive experiments are conducted on both synthetic and real data sets and the results demonstrate that JGSED outperforms the other state-of-the-art spectral clustering models, indicating the effectiveness of joint optimization.

Two-step multi-view data classification based on dynamic Graph-ELM

This paper focuses on the classification problem of multi-view data, aiming to improve the classification accuracy of current algorithms on multi-view data. Previous multi-view classification algorithms are usually based on exploiting the complementarity of different views and fusing features from different views. A representative category is the graph-based method, which builds a graph matrix for each view, and then fuses the graph matrices of different views to obtain a unified graph. These methods have the following problems: firstly, the graph matrix is simply based on sample similarity usually; secondly, the learned graph matrix does not change dynamically; thirdly, the weight of the graph representation matrix for a single view cannot be learned in the unified graph matrix. Therefore, this paper designs a Two-step classification algorithm based on Dynamic Graph-ELM, called TSDGELM. In the TSDGELM, the dynamic Graph-ELM is used to obtain the graph representation matrix of each view to save the local neighbor information of the data, and then a joint graph learning algorithm is designed based on the GBS (Graph-Based System) mechanism to fuse the graph matrix of the single-view, and finally the united graph is input into the classifier. To evaluate the effectiveness of the proposed method in this work, we conduct a series of experiments on eight datasets, and the results demonstrate the superiority of the proposed method.

Joint graph convolution networks and transformer for human pose estimation in sports technique analysis

Human pose estimation has various applications in domains such as sports technology analysis, virtual reality, and education. However, most previous studies focused on the respective feature representations of keypoints, but disregarded the topological relationship among keypoints. To address this challenge, we propose GTPose, a network structure that integrates graph convolutional networks and Transform. First of all, a set of multi-scale convolution operations are applied to extract local feature maps of images. Secondly, the positions of keypoints are roughly estimated by using Transform to process the sequential relations between feature maps. Finally, GCN is adopted to model the topological structure between keypoints to accurately locate the location of keypoints and learn feature representations. The performance of GTPose is evaluated on two real datasets: MS COCO and MPII. Experimental results demonstrate that GTPose outperforms other methods in human pose estimation tasks. In addition, experimental results also show that the spatial relationship between keypoints is effective for accurately characterizing keypoints.

Multi-ontology embeddings approach on human-aligned multi-ontologies representation for gene-disease associations prediction

ObjectivesKnowledge graphs and ontologies in the biomedical domain provide rich contextual knowledge for a variety of challenges. Employing that for knowledge-driven NLP tasks such as gene-disease association prediction represents a promising way to increase the predictive power of a model. MethodsWe investigated the power of infusing the embedding of two aligned ontologies as prior knowledge to the NLP models. We evaluated the performance of different models on some large-scale gene-disease association datasets and compared it with a model without incorporating contextualized knowledge (BERT). ResultsThe experiments demonstrated that the knowledge-infused model slightly outperforms BERT by creating a small number of bridges. Thus, indicating that incorporating cross-references across ontologies can enhance the performance of base models without the need for more complex and costly training. However, further research is needed to explore the generalizability of the model. We expected that adding more bridges would bring further improvement based on the trend we observed in the experiments. In addition, the use of state-of-the-art knowledge graph embedding methods on a joint graph from connecting OGG and DOID with bridges also yielded promising results. ConclusionOur work shows that allowing language models to leverage structured knowledge from ontologies does come with clear advantages in the performance. Besides, the annotation stage brought out in this paper is constrained in reasonable complexity.

InferLoc: Hypothesis-Based Joint Edge Inference and Localization in Sparse Sensor Networks

Ranging-based localization is a fundamental problem in the Internet of Things and unmanned aerial vehicle networks. However, the nodes’ limited-ranging scope and users’ broad coverage purpose inevitably cause network sparsity or subnetwork sparsity. The performances of existing localization algorithms are extremely unsatisfactory in sparse networks. A crucial way to deal with the sparsity is to exploit the hidden knowledge provided by the unmeasured edges, which inspires this work to propose a hypothesis-based Joint Edge Inference and Localization algorithm called InferLoc . InferLoc mines the Unmeasured but Inferable Edges (UIEs). Each UIE is an unmeasured edge, but it is restricted through other edges in the network to be inside a rigid component, so it has only a limited number of possible lengths. We propose an efficient method to detect UIEs and geometric approaches to infer possible lengths for UIEs in 2D and 3D networks. The inferred possible lengths of UIEs are then treated as multiple hypotheses to determine the node locations and the lengths of UIEs simultaneously through a joint graph optimization process. In the joint graph optimization model, to make the 0/1 decision variables for hypotheses selection differentiable, differentiable functions are proposed to relax the 0/1 selections, and rounding is applied to select the final length after the optimization converges. We also prove the condition when a UIE can contribute to sparse localization. Extensive experiments show remarkably better accuracy and efficiency performances of InferLoc than the state-of-the-art network localization algorithms. In particular, it reduces the localization errors by more than 90% and speeds up the convergence time more than 100 times than that of the widely used G2O-based methods in sparse networks.

A polynomial-time criterion for stability of large-scale switched conjunctive Boolean networks

This paper investigates the global stability of large-scale switched conjunctive Boolean networks (SCBNs) under arbitrary switching signal from the graph-theoretic perspective. With the help of node removal technique, the Thomas’ rule in Boolean case is proved, that is, a Boolean network is globally stable when its network graph is acyclic, and meanwhile the stable equilibrium is constructed. Secondly, the combination of node removal and Thomas’ rule is used to analyse the stability of each mode in SCBNs. Thirdly, when the joint graph is weakly connected and acyclic, a polynomial-time criterion is built for the global stability of large-scale SCBNs under arbitrary switching signal. Finally, the application on the SCBN model in the processing of Toll ligand Spz demonstrates the effectiveness of the criterion.

Medical federated learning with joint graph purification for noisy label learning

In terms of increasing privacy issues, Federated Learning (FL) has received extensive attention in medical imaging. Through collaborative training, FL can produce superior diagnostic models with global knowledge, while preserving private data locally. In practice, medical diagnosis suffers from intra-/inter-observer variability, thus label noise is inevitable in dataset preparation. Different from existing studies on centralized datasets, the label noise problem in FL scenarios confronts more challenges, due to data inaccessibility and even noise heterogeneity. In this work, we propose a federated framework with joint Graph Purification (FedGP) to address the label noise in FL through server and clients collaboration. Specifically, to overcome the impact of label noise on local training, we first devise a noisy graph purification on the client side to generate reliable pseudo labels by progressively expanding the purified graph with topological knowledge. Then, we further propose a graph-guided negative ensemble loss to exploit the topology of the client-side purified graph with robust complementary supervision against label noise. Moreover, to address the FL label noise with data silos, we propose a global centroid aggregation on the server side to produce a robust classifier with global knowledge, which can be optimized collaboratively in the FL framework. Extensive experiments are conducted on endoscopic and pathological images with the comparison under the homogeneous, heterogeneous, and real-world label noise for medical FL. Among these diverse noisy FL settings, our FedGP framework significantly outperforms denoising and noisy FL state-of-the-arts by a large margin. The source code is available at https://github.com/CUHK-AIM-Group/FedGP.

Joint graph entropy knowledge distillation for point cloud classification and robustness against corruptions

Classification tasks in 3D point clouds often assume that class events are independent and identically distributed (IID), although this assumption destroys the correlation between classes. This study proposes a classification strategy, Joint Graph Entropy Knowledge Distillation (JGEKD), suitable for non-independent and identically distributed 3D point cloud data, which achieves knowledge transfer of class correlations through knowledge distillation by constructing a loss function based on joint graph entropy. First, we employ joint graphs to capture the hidden relationships between classes and implement knowledge distillation to train our model by calculating the entropy of add graph. Subsequently, to handle 3D point clouds invariant to spatial transformations, we construct Siamese structures and develop two frameworks, self-knowledge distillation and teacher-knowledge distillation, to facilitate information transfer between different transformation forms of the same data. In addition, we use the above framework to achieve knowledge transfer between point clouds and their corrupted forms, and increase the robustness against corruption of model. Extensive experiments on ScanObject, ModelNet40, ScanntV2_cls and ModelNet-C demonstrate that the proposed strategy can achieve competitive results.

Difference-guided multiscale graph convolution network for unsupervised change detection in PolSAR images

Image change detection is important in polarimetric synthetic aperture radar (PolSAR) image analysis and interpretation. However, improving its accuracy is challenging because of the interference of multiplicative speckle noise. To address this issue, we propose an unsupervised PolSAR image change detection method based on a multiscale graph convolutional network (GCN). First, a Shannon entropy difference image is introduced and improved to obtain an enhanced difference image (EDI) that can effectively suppress speckle noise while preserving edge information. The generated EDI can be further utilised to construct a pseudo-label set required for unsupervised change detection. Subsequently, a difference constraint joint graph construction (DCJGC) module is proposed to obtain the object-level input information of the network. This uses the joint superpixels of multitemporal PolSAR images as graph nodes, and then introduces the difference information in the EDI to constrain the formation process of the edges between the nodes, efficiently and accurately constructing undirected graphs. Finally, a difference-guided multiscale GCN (DGMGCN) is designed for PolSAR image change detection. The network utilises difference information to eliminate the adverse effect of speckle noise on change detection and fully capture the change-aware features of multitemporal PolSAR images at fine and coarse scales, thereby improving feature discriminability. Experimental results on six real Gaofen-3 PolSAR datasets validate the superiority of the proposed approach over other state-of-the-art methods.

Privacy-Preserved Evolutionary Graph Modeling via Gromov-Wasserstein Autoregression

Real-world graphs like social networks are often evolutionary over time, whose observations at different timestamps lead to graph sequences. Modeling such evolutionary graphs is important for many applications, but solving this problem often requires the correspondence between the graphs at different timestamps, which may leak private node information, e.g., the temporal behavior patterns of the nodes. We proposed a Gromov-Wasserstein Autoregressive (GWAR) model to capture the generative mechanisms of evolutionary graphs, which does not require the correspondence information and thus preserves the privacy of the graphs' nodes. This model consists of two autoregressions, predicting the number of nodes and the probabilities of nodes and edges, respectively. The model takes observed graphs as its input and predicts future graphs via solving a joint graph alignment and merging task. This task leads to a fused Gromov-Wasserstein (FGW) barycenter problem, in which we approximate the alignment of the graphs based on a novel inductive fused Gromov-Wasserstein (IFGW) distance. The IFGW distance is parameterized by neural networks and can be learned under mild assumptions, thus, we can infer the FGW barycenters without iterative optimization and predict future graphs efficiently. Experiments show that our GWAR achieves encouraging performance in modeling evolutionary graphs in privacy-preserving scenarios.