Node Classification Research Articles

Few-shot bearing fault diagnosis by semi-supervised meta-learning with graph convolutional neural network under variable working conditions

Aiming at the problems of low accuracy and weak generalization ability in fault diagnosis caused by complex working conditions and limited fault samples of bearings, a few-shot bearing fault diagnosis method by semi-supervised meta-learning with simplifying graph convolutional neural network (semi-meta-sgc) is proposed. Firstly, the time domain signal is converted into the frequency domain by fast Fourier transform (FFT). Secondly, considering each spectrum sample as a node, a k-nearest neighbor (KNN) graph is constructed according to the adjacencies between nodes, thus transforming the bearing fault classification into a graphical node classification. Then, relying on meta-learning, graph convolutional neural network, and semi-supervised learning, a high-accuracy node classifier is obtained by using a small number of training samples to achieve the classification of bearing faults under variable working conditions. Finally, the proposed method is verified by four cases and compared with other methods. The results show that this method has higher recognition accuracy and generalization performance.

Addressing imbalance in graph datasets: Introducing GATE-GNN with graph ensemble weight attention and transfer learning for enhanced node classification

Significant challenges arise when Graph Neural Networks (GNNs) try to deal with uneven data. Specifically in signed and weighted graph structures. This makes classification tasks less effective. Within the GNN context, researchers have found traditional solutions like resampling, reweighting, and synthetic sample generation to be inadequate. GATE-GNN, a novel architecture designed specifically for imbalanced datasets, overcomes these limitations. GATE-GNN integrates an ensemble of network modules that harness the spatial features of graph networks and effectively utilise embedding information from earlier layers. This unique approach not only bolsters generalisation by reducing volatility. It also refines the optimisation algorithm, resulting in more accurate and stable classification outcomes. We rigorously tested the effectiveness of GATE-GNN on four widely recognised datasets: Cora, NELL, Citeseer, and PubMed. We performed a comparative analysis against established methods such as Graph Convolutional Networks (GCN), Graph Sample and Aggregate (GraphSAGE), Propagation Multilayer Perceptron PMLP), Imbalanced Node Sampling GNN (INS-GNN), GNN-Curriculum Learning (GNN-CL) and Graph Attention Networks (GAT). Empirical results demonstrate that GATE-GNN significantly outperforms these existing models, achieving an average improvement in classification accuracy of approximately 5%–10% over the previous best results. Additionally, GATE-GNN presents a marked reduction in training time. This underscores its efficiency and suitability for practical applications in imbalanced graph data scenarios. Implementation of the proposed GATE-GNN can be accessed here https://github.com/afofanah/GATE-GNN.

Tumor Deposits as an Adverse Prognostic Indicator in Stage III Colon Cancer: A Multicenter Database Study.

We explored the oncological impact of tumor deposits (TDs) on colon cancer and proposed optimal modifications to the current staging system. In the existing American Joint Committee on Cancer colon cancer staging system, TDs are incorporated into the N category as N1c. When lymph node metastases (LNMs) are present, their number is considered to determine nodal stages, such as N1a/b or N2a/b, regardless of TDs. 4212 patients with primary colon cancer who underwent surgical resection in the Seoul Colorectal Group (2010-2020) and 93,057 patients from the Surveillance, Epidemiology, and End Results*Stat database (2000-2017) were included in this study. Patients were classified according to the number of metastatic lymph nodes (LNs) (0/1-3/≥4) and the presence of TDs. TDs were significantly associated with left colon cancer, a higher T category, and vascular/perineural invasion. Patients with TDs had higher recurrence rates (23.1 vs 7.5%, P < 0.001). The TD-positive patients had notably worse overall survival (OS) and recurrence-free survival rates. The survival outcomes of TD-positive patients without LNM were inferior to those of TD-negative patients with LN1-3 (5-year OS: 78.9 vs 87.8%, P = 0.04). The survival outcomes of TD-positive patients with LN1-3 were similar to those of TD-negative patients with LN ≥4 (5-year OS: 87.0 vs 77.1%, P = 0.11). Survival outcomes obtained using the Surveillance, Epidemiology, and End Results *Stat database yielded consistent results. TDs were associated with poor prognostic factors and had a significant impact on survival outcomes. The incorporation of tumor deposits into nodal classifications beyond the current N1c criteria may improve the staging system and more accurately reflect the recurrence and survival rates among patients with colon cancer. TD-positive in N1a or N1b could be categorized as N2.

GNN-MgrPool: Enhanced graph neural networks with multi-granularity pooling for graph classification

Graph neural networks (GNNs) have gained sufficient attention and are applied to various domain tasks. At present, numerous pooling approaches are being proposed to aggregate node features and obtain node embeddings. However, current GNNs are black-box models that typically use a flat or single pooling step to aggregate nodes, which only considers the similarity between nodes within the cluster. These approaches ignore the influence of relationships within and between clusters in the learning process. To address this issue, we propose a novel multi-granular pooling method that aggregates nodes by simultaneously considering density and relationships among nodes and clusters. This method allows us to obtain multi-granular node-embedding clusters from GNN layers. The clusters in the current layer are built upon those in the previous layer, and these clusters change from fine to coarse as the number of clusters decreases during learning, which is achieved by using multi-granular pooling (MgrPool). Additionally, there is an inclusion relation between adjacent layers, and the node representation of each layer is established through the ratio of node distance within clusters to that between clusters. Finally, we conducted several experiments on node and graph classification tasks by combining GNN models with this pooling approach. The results demonstrate that our GNN-MgrPool model outperforms similar state-of-the-art algorithms and largely improves the interpretability of the learning process.

A cross-network node classification method in open-set scenario

Cross-network node classification aims to classify the nodes of unlabeled target network using a labeled source network. Existing methods introduce domain adaptation to address representation discrepancy in closed-set scenario. However, the open-set scenario is widespread in applications, in which, the coexistence and interaction of representation discrepancy and label discrepancy pose a great challenge. To this end, we make the first attempt for cross-network node classification in open-set scenario and propose a novel method based on reconstruction. Firstly, the pseudo unknown class nodes from target network are reconstructed into source network, which addresses label discrepancy by transforming open-set into closed-set with K+1 classes. Secondly, the contrastive-center loss is introduced to enhance the node representations, which aims to identify the unknown nodes from known nodes in networks. And then the invariant representations are learned better to address representation discrepancy. Extensive experiments demonstrate the effectiveness of our method.

Global-local graph neural networks for node-classification

The task of graph node classification is often approached by utilizing a local Graph Neural Network (GNN), that learns only local information from the node input features and their adjacency. In this paper, we propose to improve the performance of node classification GNNs by utilizing both global and local information, specifically by learning label- and node- features. We therefore call our method Global-Local-GNN (GLGNN). To learn proper label features, for each label, we maximize the similarity between its features and nodes features that belong to the label, while maximizing the distance between nodes that do not belong to the considered label. We then use the learnt label features to predict the node classification map. We demonstrate our GLGNN using three different GNN backbones, and show that our approach improves baseline performance, revealing the importance of global information utilization for node classification.

Multi-view Heterogeneous Graph Neural Networks for Node Classification

Recently, with graph neural networks (GNNs) becoming a powerful technique for graph representation, many excellent GNN-based models have been proposed for processing heterogeneous graphs, which are termed Heterogeneous graph neural networks (HGNNs). However, existing HGNNs tend to aggregate information from either direct neighbors or those connected by short metapaths, thereby neglecting the higher-order information and global feature similarity information in heterogeneous graphs. In this paper, we propose a Multi-View Heterogeneous graph neural network (MV-HGNN) to aggregate these information. Firstly, two auxiliary views, specifically a global feature similarity view and a graph diffusion view, are generated from the original heterogeneous graph. Secondly, MV-HGNN performs two message-passing strategies to get the representation of different views. Subsequently, a transformer-based aggregator is used to get the semantic information. Subsequently, the representations of the three views are fused into a final composite representation. We evaluate our method on the node classification task over three commonly used heterogeneous graph datasets, and the results demonstrate that our proposed MV-HGNN significantly outperforms state-of-the-art baselines.

Adaptive multi-scale Graph Neural Architecture Search framework

Graph neural networks (GNNs) have gained significant attention for their ability to learn representations from graph-structured data, in which message passing and feature fusion strategies play an essential role. However, traditional Graph Neural Architecture Search (GNAS) mainly focuses on optimization with a static perceptive field to ease the search process. To efficiently utilize latent relationships between non-adjacent nodes as well as edge features, this work proposes a novel two-stage approach that is able to optimize GNN structures more effectively by adaptively aggregating neighborhood features in multiple scales. This adaptive multi-scale GNAS is able to assign optimal weights for different neighbors in different graphs and learning tasks. In addition, it takes latent relationships and edge features into message passing into account, and can incorporate different feature fusion strategies. Compared with traditional ones, our proposed approach can explore a much larger and more diversified search space efficiently. We also prove that traditional multi-hop GNNs are low-pass filters, which can lead to the removal of important low-frequency components of signals from remote neighbors in a graph, and they are not even expressive enough to distinguish some simple regular graphs, justifying the superiority of our approach. Experiments with seven datasets across three graph learning tasks, including graph regression, node classification, and graph classification, demonstrate that our method yields significant improvement compared with state-of-the-art GNAS approaches and human-designed GNN approaches. Specifically, for example, with our framework, the MAE of the 12-layer AM-GNAS was 0.102 for the ZINC dataset, yielding over 25% improvement.

Research on Recognition Method of Social Robot Based on T-A-GCNIIT in the Metaverse

Social robots are used in intelligent customer service, intelligent chat, intelligent shopping guides, and more because of emotion recognition studies in cognitive psychology. However, determining the user's purpose quickly and precisely has proved challenging. Domestic researchers proposed the A-GCNII model to address missing feature information; however, it needs a lot of math. This research offers a social robot recognition approach using the T-A-GCNIIT model and cognitive psychology to optimize computing complexity and performance. The T-A-GCNIIT algorithm processes social network data, and the Viola–Jones algorithm improves social robot intelligence to represent social robots in the meta-universe. The model performs well in node classification, link prediction, community discovery, and other tasks, with enhanced accuracy, recall, F1 score value, and other metrics. The model can also better comprehend the user's emotional state using cognitive psychology to better recognize their purpose and propose a fresh notion for enhancing social robots' cognitive psychology.

Dual separated attention-based graph neural network

Graph neural networks (GNNs) offer a viable solution to model the inter-dependencies among labeled and unlabeled samples in a semi-supervised manner. However, their performances can degrade dramatically when the number of labels is extremely limited, which is due to the limitations of typical graph convolutional network design in most existing GNNs, including over-smoothing, difficulty in extending the propagation step, and failure to preserve the distinctiveness of each node. To address the issues, we propose a dual separated attention-based graph neural network (DSA-GNN) to deal with label scarcity in semi-supervised node classification. Firstly, DSA-GNN decouples feature propagation from representation transformation to alleviate the problems of over-smoothing and overfitting. Secondly, DSA-GNN separates self-representation learning from neighbor-representation learning by two feature extractors with different learnable parameters. As a result, the commonality between connected nodes and the distinctiveness of each node can be both preserved. Thirdly, DSA-GNN incorporates an attention-based label propagation mechanism to refine the label prediction of each node, by aggregating label prediction among the neighborhood based on adaptive edge coefficients. The extensive experimental results on the real-world datasets demonstrate the superiority of DSA-GNN for semi-supervised node classification, especially when the observed labels are extremely limited.

Graph Aggregating-Repelling Network: Do Not Trust All Neighbors in Heterophilic Graphs

Graph neural networks (GNNs) have demonstrated exceptional performance in processing various types of graph data, such as citation networks and social networks, etc. Although many of these GNNs prove their superiority in handling homophilic graphs, they often overlook the other kind of widespread heterophilic graphs, in which adjacent nodes tend to have different classes or dissimilar features. Recent methods attempt to address heterophilic graphs from the graph spatial domain, which try to aggregate more similar nodes or prevent dissimilar nodes with negative weights. However, they may neglect valuable heterophilic information or extract heterophilic information ineffectively, which could cause poor performance of downstream tasks on heterophilic graphs, including node classification and graph classification, etc. Hence, a novel framework named GARN is proposed to effectively extract both homophilic and heterophilic information. First, we analyze the shortcomings of most GNNs in tackling heterophilic graphs from the perspective of graph spectral and spatial theory. Then, motivated by these analyses, a Graph Aggregating-Repelling Convolution (GARC) mechanism is designed with the objective of fusing both low-pass and high-pass graph filters. Technically, it learns positive attention weights as a low-pass filter to aggregate similar adjacent nodes, and learns negative attention weights as a high-pass filter to repel dissimilar adjacent nodes. A learnable integration weight is used to adaptively fuse these two filters and balance the proportion of the learned positive and negative weights, which could control our GARC to evolve into different types of graph filters and prevent it from over-relying on high intra-class similarity. Finally, a framework named GARN is established by simply stacking several layers of GARC to evaluate its graph representation learning ability on both the node classification and image-converted graph classification tasks. Extensive experiments conducted on multiple homophilic and heterophilic graphs and complex real-world image-converted graphs indicate the effectiveness of our proposed framework and mechanism over several representative GNN baselines.

Dual-source dual-energy CT and deep learning for equivocal lymph nodes on CT images for thyroid cancer.

This study investigated the diagnostic performance of dual-energy computed tomography (CT) and deep learning for the preoperative classification of equivocal lymph nodes (LNs) on CT images in thyroid cancer patients. In this prospective study, from October 2020 to March 2021, 375 patients with thyroid disease underwent thin-section dual-energy thyroid CT at a small field of view (FOV) and thyroid surgery. The data of 183 patients with 281 LNs were analyzed. The targeted LNs were negative or equivocal on small FOV CT images. Six deep-learning models were used to classify the LNs on conventional CT images. The performance of all models was compared with pathology reports. Of the 281 LNs, 65.5% had a short diameter of less than 4 mm. Multiple quantitative dual-energy CT parameters significantly differed between benign and malignant LNs. Multivariable logistic regression analyses showed that the best combination of parameters had an area under the curve (AUC) of 0.857, with excellent consistency and discrimination, and its diagnostic accuracy and sensitivity were 74.4% and 84.2%, respectively (p < 0.001). The visual geometry group 16 (VGG16) based model achieved the best accuracy (86%) and sensitivity (88%) in differentiating between benign and malignant LNs, with an AUC of 0.89. The VGG16 model based on small FOV CT images showed better diagnostic accuracy and sensitivity than the spectral parameter model. Our study presents a noninvasive and convenient imaging biomarker to predict malignant LNs without suspicious CT features in thyroid cancer patients. Our study presents a deep-learning-based model to predict malignant lymph nodes in thyroid cancer without suspicious features on conventional CT images, which shows better diagnostic accuracy and sensitivity than the regression model based on spectral parameters. Many cervical lymph nodes (LNs) do not express suspicious features on conventional computed tomography (CT). Dual-energy CT parameters can distinguish between benign and malignant LNs. Visual geometry group 16 model shows superior diagnostic accuracy and sensitivity for malignant LNs.

REFUEL: rule extraction for imbalanced neural node classification

Imbalanced graph node classification is a highly relevant and challenging problem in many real-world applications. The inherent data scarcity, a central characteristic of this task, substantially limits the performance of neural classification models driven solely by data. Given the limited instances of relevant nodes and complex graph structures, current methods fail to capture the distinct characteristics of node attributes and graph patterns within the underrepresented classes. In this article, we propose REFUEL—a novel approach for highly imbalanced node classification problems in graphs. Whereas symbolic and neural methods have complementary strengths and weaknesses when applied to such problems, REFUEL combines the power of symbolic and neural learning in a novel neural rule-extraction architecture. REFUEL captures the class semantics in the automatically extracted rule vectors. Then, REFUEL augments the graph nodes with the extracted rules vectors and adopts a Graph Attention Network-based neural node embedding, enhancing the downstream neural node representation. Our evaluation confirms the effectiveness of the proposed REFUEL approach for three real-world datasets with different minority class sizes. REFUEL achieves at least a 4% point improvement in precision on the minority classes of 1.5–2% compared to the baselines.

HealthGAT: Node Classifications in Electronic Health Records using Graph Attention Networks.

While electronic health records (EHRs) are widely used across various applications in healthcare, most applications use the EHRs in their raw (tabular) format. Relying on raw or simple data pre-processing can greatly limit the performance or even applicability of downstream tasks using EHRs. To address this challenge, we present HealthGAT, a novel graph attention network framework that utilizes a hierarchical approach to generate embeddings from EHR, surpassing traditional graph-based methods. Our model iteratively refines the embeddings for medical codes, resulting in improved EHR data analysis. We also introduce customized EHR-centric auxiliary pre-training tasks to leverage the rich medical knowledge embedded within the data. This approach provides a comprehensive analysis of complex medical relationships and offers significant advancement over standard data representation techniques. HealthGAT has demonstrated its effectiveness in various healthcare scenarios through comprehensive evaluations against established methodologies. Specifically, our model shows outstanding performance in node classification and downstream tasks such as predicting readmissions and diagnosis classifications.

A Fully Test-time Training Framework for Semi-supervised Node Classification on Out-of-Distribution Graphs

Graph neural networks (GNNs) have shown great potential in representation learning for various graph tasks. However, the distribution shift between the training and test sets poses a challenge to the efficiency of GNNs. To address this challenge, HomoTTT proposes a fully test-time training framework for GNNs to enhance the model’s generalization capabilities for node classification tasks. Specifically, our proposed HomoTTT designs a homophily-based and parameter-free graph contrastive learning task with adaptive augmentation to guide the model’s adaptation during the test-time training, allowing the model to adapt for specific target data. In the inference stage, HomoTTT proposes to integrate the original GNN model and the adapted model after TTT using a homophily-based model selection method, which prevents potential performance degradation caused by unconstrained model adaptation. Extensive experimental results on six benchmark datasets demonstrate the effectiveness of our proposed framework. Additionally, the exploratory study further validates the rationality of the homophily-based graph contrastive learning task with adaptive augmentation and the homophily-based model selection designed in HomoTTT .

High-order proximity and relation analysis for cross-network heterogeneous node classification

High-order proximity and relation analysis for cross-network heterogeneous node classification

FairGAT: Fairness-Aware Graph Attention Networks

Graphs can facilitate modeling various complex systems such as gene networks and power grids as well as analyzing the underlying relations within them. Learning over graphs has recently attracted increasing attention, particularly graph neural network (GNN)–based solutions, among which graph attention networks (GATs) have become one of the most widely utilized neural network structures for graph-based tasks. Although it is shown that the use of graph structures in learning results in the amplification of algorithmic bias, the influence of the attention design in GATs on algorithmic bias has not been investigated. Motivated by this, the present study first carries out a theoretical analysis in order to demonstrate the sources of algorithmic bias in GAT-based learning for node classification. Then, a novel algorithm, FairGAT, which leverages a fairness-aware attention design, is developed based on the theoretical findings. Experimental results on real-world networks demonstrate that FairGAT improves group fairness measures while also providing comparable utility to the fairness-aware baselines for node classification and link prediction.

Mixed Graph Contrastive Network for Semi-supervised Node Classification

Graph Neural Networks (GNNs) have achieved promising performance in semi-supervised node classification in recent years. However, the problem of insufficient supervision, together with representation collapse, largely limits the performance of the GNNs in this field. To alleviate the collapse of node representations in semi-supervised scenario, we propose a novel graph contrastive learning method, termed M ixed G raph C ontrastive N etwork (MGCN). In our method, we improve the discriminative capability of the latent embeddings by an interpolation-based augmentation strategy and a correlation reduction mechanism. Specifically, we first conduct the interpolation-based augmentation in the latent space and then force the prediction model to change linearly between samples. Second, we enable the learned network to tell apart samples across two interpolation-perturbed views through forcing the correlation matrix across views to approximate an identity matrix. By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discriminative representation learning. Extensive experimental results on six datasets demonstrate the effectiveness and the generality of MGCN compared to the existing state-of-the-art methods. The code of MGCN is available at https://github.com/xihongyang1999/MGCN on Github.

Nia-GNNs: neighbor-imbalanced aware graph neural networks for imbalanced node classification

Nia-GNNs: neighbor-imbalanced aware graph neural networks for imbalanced node classification

Predicting properties of nodes via community-aware features

This paper shows how information about the network’s community structure can be used to define node features with high predictive power for classification tasks. To do so, we define a family of community-aware node features and investigate their properties. Those features are designed to ensure that they can be efficiently computed even for large graphs. We show that community-aware node features contain information that cannot be completely recovered by classical node features or node embeddings (both classical and structural) and bring value in node classification tasks. This is verified for various classification tasks on synthetic and real-life networks.