Nodes In Graph Research Articles

Enhancing the Recognition of Collinear Building Patterns by Shape Cognition Based on Graph Neural Networks

ABSTRACT Building patterns are important components of urban structures and functions, and their accurate recognition is the foundation of urban spatial analysis, cartographic generalization, and other tasks. Current building pattern recognition methods are often based on a shape index that can only characterize shape features from one aspect, resulting in significant errors. In this study, a building pattern recognition method based on a graph neural network is proposed to enhance shape cognition and focus on recognizing collinear patterns. First, a building shape classification model that integrates global shape and graph node structure features was constructed to quantitatively study shape cognition. Subsequently, a collinear pattern recognition (CPR) model was established based on a dual building graph. The shape cognition results were integrated into the model to enhance its recognition ability. The results show that the shape classification model can be used to effectively distinguish different shape categories and support building pattern recognition tasks. Based on the CPR model, false recognitions can be avoided, and recognition results similar to those of visual cognition can be obtained. Compared with the comparative methods, both models have significant advantages in terms of statistical results and implementation.

Towards Improving the Efficiency of Drug Repurposing by Leveraging Node Promiscuity in Biomedical Knowledge Graphs

To accelerate the time- and labor-intensive processes of drug discovery and repurposing, it is increasingly common to mine knowledge sources for connections between diseases and the drugs that can treat them. In this paper we address the scalability challenge in the connection mining, by introducing algorithms that can be used to find plausible mechanistic connections between drugs and the potentially associated diseases in biomedical knowledge graphs. These connections are then presented to biomedical experts as candidate hypotheses for further studies of whether the drugs can be repurposed to treat the diseases. One challenge that has to be addressed in this effort is the processing of promiscuous knowledge-graph nodes, that is, nodes associated with numerous relationships that may not be unique or indicative of the node properties. As it turns out, the multiplicity of relationships involving promiscuous graph nodes may prevent the aforementioned path-finding algorithms from aiding in drug repurposing. To address the promiscuous-node challenge, we introduce promiscuity scores for nodes and paths in knowledge graphs, and incorporate the scores in the proposed path-finding algorithms. We report experimental results that indicate that paths with low promiscuity scores could be meaningful and of interest to biomedical experts in drug repurposing.

Effective geometry of Bell-network states on a dipole graph

Abstract Bell-network states are a class of entangled states of the geometry that satisfy an area-law for the entanglement entropy in a limit of large spins and are automorphism-invariant, for arbitrary graphs. We present a comprehensive analysis of the effective geometry of Bell-network states on a dipole graph. Our main goal is to provide a detailed characterization of the quantum geometry of a class of diffeomorphism-invariant, area-law states representing homogeneous and isotropic configurations in loop quantum gravity, which may be explored as boundary states for the dynamics of the theory. We found that the average geometry at each node in the dipole graph does not match that of a flat tetrahedron. Instead, the expected values of the geometric observables satisfy relations that are characteristic of spherical tetrahedra. The mean geometry is accompanied by fluctuations with considerable relative dispersion for the dihedral angle, and perfectly correlated for the two nodes.

Graph-DTI: A New Model for Drug-target Interaction Prediction Based on Heterogenous Network Graph Embedding.

In this study, we aimed to develop a new end-to-end learning model called Graph-Drug-Target Interaction (DTI), which integrates various types of information in the heterogeneous network data, and to explore automatic learning of the topology-maintaining representations of drugs and targets, thereby effectively contributing to the prediction of DTI. Precise predictions of DTI can guide drug discovery and development. Most machine learning algorithms integrate multiple data sources and combine them with common embedding methods. However, the relationship between the drugs and target proteins is not well reported. Although some existing studies have used heterogeneous network graphs for DTI prediction, there are many limitations in the neighborhood information between the nodes in the heterogeneous network graphs. We studied the drug-drug interaction (DDI) and DTI from DrugBank Version 3.0, protein-protein interaction (PPI) from the human protein reference database Release 9, drug structure similarity from Morgan fingerprints of radius 2 and calculated by RDKit, and protein sequence similarity from Smith-Waterman score. Our study consists of three major components. First, various drugs and target proteins were integrated, and a heterogeneous network was established based on a series of data sets. Second, the graph neural networks-inspired graph auto-encoding method was used to extract high-order structural information from the heterogeneous networks, thereby revealing the description of nodes (drugs and proteins) and their topological neighbors. Finally, potential DTI prediction was made, and the obtained samples were sent to the classifier for secondary classification. The performance of Graph-DTI and all baseline methods was evaluated using the sums of the area under the precision-recall curve (AUPR) and the area under the receiver operating characteristic curve (AUC). The results indicated that Graph-DTI outperformed the baseline methods in both performance results. Compared with other baseline DTI prediction methods, the results showed that Graph-DTI had better prediction performance. Additionally, in this study, we effectively classified drugs corresponding to different targets and vice versa. The above findings showed that Graph-DTI provided a powerful tool for drug research, development, and repositioning. Graph- DTI can serve as a drug development and repositioning tool more effectively than previous studies that did not use heterogeneous network graph embedding.

Nondeterminism and the Clique Problem

The Clique problem is known to be NP-Complete [7,3] and the question whether P=NP is unresolved. This paper examines the relative power of nondeterminism versus determinism in a restricted setting. Specifically, we consider solving the clique problem using non-deterministic and deterministic Turing machines. We impose a (reasonable) format in which a problem instance is encoded. We also impose constraints on the computation of both deterministic and non-deterministic Turing machines: both have two tapes, the input tape is read-only and one-way, and once a certain stop point in the input tape is reached, no additional writing on the work tape is allowed. We consider two cases for the position of the stop point: immediately after the number of graph nodes and the size of the clique are specified, or controlled by a parameter q that indicates what portion of the graph nodes' edge specifications have been scanned. The parameter q may be arbitrarily close to 1, e.g., q=0.99999. We show, for both cases in our setting, that a non-deterministic Turing machine can solve the problem in O(n3) time whereas no deterministic Turing machine can solve the problem in polynomial time. However, we exhibit an exponential time deterministic single work tape, two-heads Turing machine that solves the clique problem in our setting.

Automated message selection for robust Heterogeneous Graph Contrastive Learning

Heterogeneous Graph Contrastive Learning (HGCL) has attracted lots of attentions because of eliminating the requirement of node labels. The encoders used in HGCL mainly are message-passing based Heterogeneous Graph Neural Networks, which are vulnerable to edge perturbations. Recently, a few HGCL models replace the polluted graph with KNN graph or threshold graph, which both have flaws: (1) each node in KNN graph have the same degree K, it is irrational and loses original structural features; (2) the threshold is selected artificially, which hinders both effectiveness and interpretability. To tackle the above issues, we propose an Automated Message Selection based Heterogeneous Graph Contrastive Learning (AMS-HGCL) model. We first set relation view and meta-path view for contrast. Then, a robust encoder is proposed to defend structural attacks for both views by automatically selecting harmless messages, without setting all nodes having the same number of neighbors. The learned probabilities of messages can show harmful features directly, which makes our model interpretable. Finally, we design a novel cross-view contrastive loss to optimize AMS-HGCL and output robust node representations. The experimental results on four real datasets demonstrate that AMS-HGCL is feasible and effective.

Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective

Graph neural networks (GNNs) based on message-passing mechanisms have achieved advanced results in graph classification tasks. However, their generalization performance degrades when noisy labels are present in the training data. Most existing noisy labeling approaches focus on the visual domain or graph node classification tasks and analyze the impact of noisy labels only from a utility perspective. Unlike existing work, in this paper, we measure the effects of noise labels on graph classification from data privacy and model utility perspectives. We find that noise labels degrade the model’s generalization performance and enhance the ability of membership inference attacks on graph data privacy. To this end, we propose the robust graph neural network (RGLC) approach with noisy labeled graph classification. Specifically, we first accurately filter the noisy samples by high-confidence samples and the first feature principal component vector of each class. Then, the robust principal component vectors and the model output under data augmentation are utilized to achieve noise label correction guided by dual spatial information. Finally, supervised graph contrastive learning is introduced to enhance the embedding quality of the model and protect the privacy of the training graph data. The utility and privacy of the proposed method are validated by comparing twelve different methods on eight real graph classification datasets. Compared with the state-of-the-art methods, the RGLC method achieves at most and at least 7.8% and 0.8% performance gain at 30% noisy labeling rate, respectively, and reduces the accuracy of privacy attacks to below 60%.

Superpixel semantics representation and pre-training for vision–language tasks

The key to integrating visual language tasks is to establish a good alignment strategy. Recently, visual semantic representation has achieved fine-grained visual understanding by dividing grids or image patches. However, the coarse-grained semantic interactions in image space should not be ignored, which hinders the extraction of complex contextual semantic relations at the scene boundaries. This paper proposes superpixels as comprehensive and robust visual primitives, which mine coarse-grained semantic interactions by clustering perceptually similar pixels, speeding up the subsequent processing of primitives. To capture superpixel-level semantic features, we propose a Multiscale Difference Graph Convolutional Network (MDGCN). It allows parsing the entire image as a fine-to-coarse visual hierarchy. To reason actual semantic relations, we reduce potential noise interference by aggregating difference information between adjacent graph nodes. Finally, we propose a multi-level fusion rule in a bottom-up manner to avoid understanding deviation by mining complementary spatial information at different levels. Experiments show that the proposed method can effectively promote the learning of multiple downstream tasks. Encouragingly, our method outperforms previous methods on all metrics.

Masked Graph Autoencoder for Self‐Supervised Transportation Mode Recognition

ABSTRACTTransportation mode recognition reveals the traveling patterns of urban residents and plays an important role in travel analysis and city planning. Research has been done to identify transportation modes using deep learning methods. However, large‐scale and far‐ranging labeled trajectory data are hard to acquire, which hinders the training and application of supervised models. In this study, we propose a self‐supervised method for trajectory transportation modes recognition. First, we construct sequence and dependency graph for trajectory points. Next, we apply mask and remask strategy to graph node features to enhance its learning ability in semantic information. Notably, in order to learn features without labeled data, we introduce graph autoencoder into the framework. This method is able to learn the sequence and dependency feature reconstruction of the travel paths. It can obtain underlying semantic information with the mask and remask strategy. We applied our model to GPS trajectory dataset from the Microsoft GeoLife Project, achieving an average accuracy of 68.26% in identifying the transportation modes among seven categories. The result indicates that the proposed method offers a solution to identifying transportation modes without abundant labeled data. This method can also help to extract space–time features at different scales from trajectory data, which could be applied to various downstream tasks.

A robust self-training algorithm based on relative node graph

A robust self-training algorithm based on relative node graph

MaskDGNets: Masked-attention guided dynamic graph aggregation network for event extraction.

Considering that the traditional deep learning event extraction method ignores the correlation between word features and sequence information, it cannot fully explore the hidden associations between events and events and between events and primary attributes. To solve these problems, we developed a new framework for event extraction called the masked attention-guided dynamic graph aggregation network. On the one hand, to obtain effective word representation and sequence representation, an interaction and complementary relationship are established between word vectors and character vectors. At the same time, a squeeze layer is introduced in the bidirectional independent recurrent unit to model the sentence sequence from both positive and negative directions while retaining the local spatial details to the maximum extent and establishing practical long-term dependencies and rich global context representations. On the other hand, the designed masked attention mechanism can effectively balance the word vector features and sequence semantics and refine these features. The designed dynamic graph aggregation module establishes effective connections between events and events, and between events and essential attributes, strengthens the interactivity and association between them, and realizes feature transfer and aggregation on graph nodes in the neighborhood through dynamic strategies to improve the performance of event extraction. We designed a reconstructed weighted loss function to supervise and adjust each module individually to ensure the optimal feature representation. Finally, the proposed MaskDGNets framework is evaluated on two baseline datasets, DuEE and CCKS2020. It demonstrates its robustness and event extraction performance, with F1 of 81.443% and 87.382%, respectively.

Fault diagnosis of rolling bearings under variable operating conditions based on improved graph neural networks

Abstract To address the issues of low diagnostic accuracy, insufficient generalization, and poor robustness in traditional fault diagnosis methods across different equipment and varying operating conditions, this paper proposes an improved graph neural network-based fault diagnosis method for rolling bearings to enhance model performance under complex conditions. First, the optimized wavelet transform coefficient features are used as nodes, and by exploring the correlations between features, node adjacency relationships are constructed. The associations between fault modes and feature node graphs under different conditions are studied, and a fault feature graph sample set based on subgraph structures is built, providing data for the subsequent graph neural network learning. Then, a multi-head attention mechanism (MHGAT) and multi-scale feature adaptive perception pooling (MSF-ASAP) are integrated to construct a multi-head graph attention mechanism model based on multi-scale feature adaptive perception pooling (MSM-GAT). MHGAT enhances the model's ability to perceive global information by learning different features from multiple perspectives and dimensions, thus improving the model's generalization. MSF-ASAP adaptively selects and aggregates information at multiple scales, enabling the model to effectively extract key features under various operating conditions, resist noise interference, and adapt to local information changes, thus improving the model's robustness under varying conditions and noisy environments. Experimental results under multiple and continuously varying conditions demonstrate that the proposed method outperforms traditional methods in terms of diagnostic accuracy and robustness. Notably, it exhibits excellent generalization when identifying unknown conditions, achieving over 95% accuracy in recognizing new conditions and maintaining over 92.5% accuracy in noisy environments.

Physics-guided spatiotemporal approach for melt pool size prediction in laser powder bed fusion

ABSTRACT This study first proposes a physics-guided spatiotemporal graph. The melt pool temporal feature nodes and spatial feature nodes are extracted from melt pool images based on spatiotemporal correlations. These feature points are treated as graph nodes, and the edge weights in the graph are calculated based on an analytical heat transfer model. It supplements the physical information of accumulated heat. Based on this, the graph convolutional network (GCN) is used to extract spatiotemporal information of heat transfer, and the long short-term memory (LSTM) is used to capture the evolution patterns of the melt pool. Thus, a melt pool spatiotemporal feature extraction model is constructed for melt pool size prediction. The model achieves prediction errors within 12% for the melt pool area and 8.5% for the melt pool perimeter. Subsequently, interpretability analysis indicates that the physics-guided approach enhances the model's learning ability for the cumulative contribution of heat from neighboring tracks.

Dynamic Spatio-Temporal Hypergraph Convolutional Network for Traffic Flow Forecasting

Graph convolutional networks (GCN) are an important research method for intelligent transportation systems (ITS), but they also face the challenge of how to describe the complex spatio-temporal relationships between traffic objects (nodes) more effectively. Although most predictive models are designed based on graph convolutional structures and have achieved effective results, they have certain limitations in describing the high-order relationships between real data. The emergence of hypergraphs breaks this limitation. A dynamic spatio-temporal hypergraph convolutional network (DSTHGCN) model is proposed in this paper. It models the dynamic characteristics of traffic flow graph nodes and the hyperedge features of hypergraphs simultaneously, achieving collaborative convolution between graph convolution and hypergraph convolution (HGCN). On this basis, a hyperedge outlier removal mechanism (HOR) is introduced during the process of node information propagation to hyper-edges, effectively removing outliers and optimizing the hypergraph structure while reducing complexity. Through in-depth experimental analysis on real-world datasets, this method has better performance compared to other methods.

Local error analysis of L1 scheme for time-fractional diffusion equation on a star-shaped pipe network

Abstract The numerical analysis for differential equations on networks has become a significant issue in theory and diverse fields of applications. Nevertheless, solving time-fractional diffusion problem on metric graphs has been less studied so far, as one of the major challenging tasks of this problem is the weak singularity of solution at initial moment. In order to overcome this difficulty, a new L1-finite difference method considering the weak singular solution at initial time is proposed in this paper. Specifically, we utilize this method on temporal graded meshes and spacial uniform meshes, which has a new treatment at the junction node of metric graph by employing Taylor expansion method, Neumann-Kirchhoff and continuity conditions. Over the whole star graph, the optimal error estimate of this fully discrete scheme at each time step is given. Also, the convergence analysis for a discrete scheme that preserves the Neumann-Kirchhoff condition at each time level is demonstrated. Finally, numerical results show the effectiveness of proposed full-discrete scheme, which can be applied to star graphs and even more general graphs with multiple cross points.

RMGANets: reinforcement learning-enhanced multi-relational attention graph-aware network for anti-money laundering detection

Given the anonymity and complexity of illegal transactions, traditional deep-learning methods struggle to establish correlations between transaction addresses, cash flows, and physical users. Additionally, the limited number of labels for illegal transactions results in severe class imbalance and other challenges. To overcome these limitations, we propose a reinforcement learning-enhanced, multi-relational, attention graph-aware framework to detect anti-money laundering and illegal trading activities. On the one hand, a data-driven, graph-aware layer establishes long-term dependencies and correlations between transaction graph nodes. Similarity among graph nodes divides the topological graph into three subgraphs. Learning from these subgraphs and converging nodes enriches local, global, and contextual details. Simultaneously, using repeated nodes across the subgraphs enhances interactivity between them, reduces intra-class ambiguity, and accentuates inter-class differences. On the other hand, a reinforcement learning module embedded in the graph-aware layer compensates for the missing details in node features caused by masking operations. Furthermore, the reconstructed loss function addresses significant classification inaccuracies by reducing the weight assigned to easily classified samples. Balancing these issues and individually supervising each component enables the detection framework to achieve optimal performance. The evaluation results demonstrate that our proposed model exhibits optimal detection performance and robustness, such as F1 of 93.85% and 94.39%.

Dynamic graph spatial-temporal dependence information extraction for remaining useful life prediction of rolling bearings

As a powerful tool for learning high-dimensional data representation, graph neural networks (GNN) have been applied to predict the remaining useful life (RUL) of rolling bearings. Existing GNN-based RUL prediction methods predominantly rely on constant pre-constructed graphs. However, the degradation of bearings is a dynamic process, and the dependence information between features may change at different moments of degradation. This article introduces a method for RUL prediction based on dynamic graph spatial-temporal dependence information extraction. The raw signal is segmented into multiple periods, and multiple features of each period data are extracted. Then, the correlation coefficient analysis is conducted, and the feature connection graph of each period is constructed based on different analytical results, thereby dynamically mapping the degradation process. The graph data is fed into graph convolutional networks (GCN) to extract spatial dependence between the graph node features in different periods. To make up for the shortcomings of GCN in temporal dependence extraction, the TimesNet module is introduced. TimesNet considers the two-dimensional changes of time series data and can extract the temporal dependence of graph data within and between different time cycles. Experimental results based on the PHM2012 dataset show that the average RUL prediction error of the proposed method is 17.4%, outperforming other comparative methods.

A Strategy for Network multi-layer Information Fusion Based on Multimodel in User Emotional Polarity Analysis

Emotional analysis is an important research direction in natural language processing, which aims to automatically recognize and understand emotions and emotional polarity in texts. The study employed multiple emotional analysis models to analyze emotions in text data. Then the emotional analysis results of different models were integrated to improve accuracy through a hierarchical information fusion strategy. Meanwhile, graph embedding algorithms such as DeepWalk and Node2vec were utilized to process node information in graph data. The embedding representation of graph nodes was utilized for emotional analysis of nodes. In addition, based on models such as graph convolutional neural networks for message passing, contextual information of nodes was obtained to improve emotional analysis performance. These results indicated that the proportion of passive users was higher than that of active users, at 57.14% and 39.68%, respectively. Despite the large number of negative users, the frequency of connections between active users was significantly higher than between negative users. Multiple algorithms were utilized for emotional analysis and prediction. The AUC curve performed well, but the accuracy was only 56.69%, which needs improvement. The study also evaluated the root mean square error of network predictions, with errors typically below 0.2 in large networks, demonstrating relatively accurate prediction results. This guides the further development of emotional analysis technology, promoting the research and improvement of more accurate and reliable emotional analysis methods.

Knowledge based attribute completion for heterogeneous graph node classification

Heterogeneous graphs, with diverse node and edge types, are prevalent in real-world scenarios. Graph Neural Networks have gained significant attention for processing such complex data structures, delivering impressive results across various tasks like node classification. However, current GNN approaches overlook quality concerns within heterogeneous graphs, like noise or missing attributes, which directly affect the performance of downstream tasks. Previous research has attempted to address these challenges by employing simple one-hot embedding, which is disconnected from the original graph and prone to introducing noise. However, the improvements brought by these methods are limited when the quality of the original graph itself is poor. To this end, we propose a novel attribute completion method based on external knowledge bases, which incorporates a knowledge based completion framework with a relation-aware attention mechanism. The model first employs an attention mechanism to embed the external knowledge subgraph related to the topological structure of the original graph. Then, for nodes requiring attribute completion, the model leverages the association between the external knowledge base and the original graph to complete the missing attributes. Our proposed method can be combined with existing heterogeneous graph neural networks to enhance their performance. Extensive node classification experiments on three real-world datasets underscore the superior performance of our proposed method.

Boosting Graph Contrastive Learning via Adaptive Sampling.

Contrastive learning (CL) is a prominent technique for self-supervised representation learning, which aims to contrast semantically similar (i.e., positive) and dissimilar (i.e., negative) pairs of examples under different augmented views. Recently, CL has provided unprecedented potential for learning expressive graph representations without external supervision. In graph CL, the negative nodes are typically uniformly sampled from augmented views to formulate the contrastive objective. However, this uniform negative sampling strategy limits the expressive power of contrastive models. To be specific, not all the negative nodes can provide sufficiently meaningful knowledge for effective contrastive representation learning. In addition, the negative nodes that are semantically similar to the anchor are undesirably repelled from it, leading to degraded model performance. To address these limitations, in this article, we devise an adaptive sampling strategy termed "AdaS." The proposed AdaS framework can be trained to adaptively encode the importance of different negative nodes, so as to encourage learning from the most informative graph nodes. Meanwhile, an auxiliary polarization regularizer is proposed to suppress the adverse impacts of the false negatives and enhance the discrimination ability of AdaS. The experimental results on a variety of real-world datasets firmly verify the effectiveness of our AdaS in improving the performance of graph CL.