Abstract: With the wide application of graph neural network (GNN) in many fields, how to extract and aggregate node features effectively has become a hot research issue. In this paper, we propose a ...

1 College of Computer Science and Engineering, Changsha University, Changsha, Hunan, China 2 Department of Information and Computing Science, College of Mathematics, Changsha University, Changsha, ...

Hyperspectral images (HSIs) have very high dimensionality and typically lack sufficient labeled samples, which significantly challenges their processing and analysis. These challenges contribute to ...

As a classical multi-agent game model, the evolutionary minority game(EMG) has wide applications in financial markets and distributed control systems. The factors that influence the systematic ...

The problem of over-smoothing has emerged as a fundamental issue for Graph Convolutional Networks (GCNs). While existing efforts primarily focus on enhancing the discriminability of node ...