Structure-Adaptive Multi-View Graph Clustering for Remote Sensing Data

Multi-view clustering (MVC) for remote sensing data is a critical and challenging task in Earth observation. Although recent advances in graph neural network (GNN)-based MVC have shown remarkable success, most prevalent approaches have two major limitations: 1) heavily relying on a predefined yet fixed graph, which limits the clustering performance because the large number of indistinguishable background samples contained in remote sensing data would introduce noise information and increase structure heterogeneity; 2) ignoring the effect of confusing samples on cluster structure compactness, which leads to fluffy cluster structure and decreases feature discriminability. To address these issues, we propose a Structure-Adaptive Multi-View Graph Clustering method named SAMVGC on remote sensing data, which boosts the structure homogeneity and cluster compactness by adaptively learning the graph and cluster structures, respectively. Concretely, we use the geometric structure within the feature embedding space to refine adjacency matrices. The adjacency matrices are dynamically fused with the previous ones to improve the homogeneity and stability of structure information. Additionally, the samples are separated into two categories, including the central ones (i.e., intra-cluster center samples) and the confusing ones (i.e., inter-cluster boundary samples). On this basis, to improve the cluster compactness and consistency, we deploy the contrastive learning paradigm on the central samples within views and the consistent learning paradigm on the confusing samples between views. Finally, we conduct extensive experiments on four benchmarks and achieve promising results, well demonstrating the effectiveness and superiority of the proposed method.