Graph Decipher: A transparent dual‐attention graph neural network to understand the message‐passing mechanism for the node classification

Abstract

Graph neural networks (GNNs) can be effectively applied to solve many real-world problems across widely diverse fields. Their success is inseparable from the message-passing mechanisms evolving over the years. However, current mechanisms treat all node features equally at the macro-level (node-level), and the optimal aggregation method has not yet been explored. In this paper, we propose a new GNN called Graph Decipher (GD), which transparentizes the message flows of node features from micro-level (feature-level) to global-level and boosts the performance on node classification tasks.Besides, to reduce the computational burden caused by investigating message-passing, only the relevant representative node attributes are extracted by graph feature filters, allowing calculations to be performed in a category-oriented manner. Experiments on 10 node classification data sets show that GD achieves state-ofthe-art performance while imposing a substantially lower computational cost. Additionally, since GD has the ability to explore the representative node attributes

Node Importance Estimation with Multiview Contrastive Representation Learning

“…Graph neural networks (GNNs) apply deep learning ideas to graph data, and these methods have attracted great research attention in recent years [17][18][19]. Te pioneering work of GNN is the graph convolution model GCN [20], which performs convolution in the Fourier domain by aggregating neighbor node features and has performed well in many applications.…”

DAG: Dual Attention Graph Representation Learning for Node Classification

“…The graph adjacency matrix (GAM) is a widely used representation of node relationships in graphs, providing insights into the graph's structure and features. However, the GAM has limitations in effectively incorporating the influences of multiple adjacent vertices on a target vertex [40]. To overcome this limitation, attention-based methods like GTN have emerged.…”

“…Non-attention-based methods, including Cleora [55] and 3ference [56], have also shown promising results. Additionally, Graph Decipher (GD) [40], which primarily focuses on node classification in imbalanced multiclass graph datasets, stands out due to its ability to investigate categoryspecific features by exploring representative node attributes. Despite the continuous improvement in the most advanced methods, our DAG method exhibited competitive performance.…”

“…It can be observed that the MLP, the only non-GNN method, performed relatively poorly. On the other hand, MoNet, GCN, GraphSAGE, GAT, and GD [28,29,32,40,63] all considered the mechanism of information propagation between nodes in the graph. They achieved significantly higher accuracy rates on all four datasets, especially Graph Decipher, which achieved accuracy rates of 95.9%, 97.3%, 83.1%, and 89.3%, respectively.…”

Cam-PC: A Novel Method for Camouflaging Point Clouds to Counter Adversarial Deception in Remote Sensing

“…Compared to the regular format of three-dimensional data, point cloud data is less affected by lighting and image quality, and it contains less redundant data, thus significantly reducing computing and storage costs. Point cloud data is widely used in various fields, including 3D matching [2], [3], multi-view 3D reconstruction [4], [5], object detection and recognition [6]- [8], and semantic segmentation [9]- [11], graph tasks [12], [13], etc. In the field of remote sensing, synthetic aperture radar generates the point cloud data of a target by utilizing interferometric measurement technology to image the same area of the target object twice and forming a certain geometric relationship between the interferograms and the height, wavelength, and beam direction parameters of the sensor [14], [15].…”