Deep Fair Multi-View Clustering with Attention KAN

Multi-view clustering, while effective in integrating information from diverse data sources, may lead to biased outcomes when sensitive attributes are involved. Despite the substantial progress in recent research, most existing methods suffer from limited interpretability and lack strong mathematical theoretical foundations. In this work, we propose a novel approach, \textbf{D}eep \textbf{F}air \textbf{M}ulti-\textbf{V}iew \textbf{C}lustering with \textbf{A}ttention \textbf{K}olmogorov-\textbf{A}rnold \textbf{N}etwork (DFMVC-AKAN), designed to generate fair clustering results while maintaining robust performance. DFMVC-AKAN integrates attention mechanisms with multi-view data reconstruction to enhance both clustering accuracy and fairness. The model introduces an attention mechanism and Kolmogorov-Arnold Networks (KAN), which together address the challenges of feature fusion and the influence of sensitive attributes in multi-view data. The attention mechanism enables the model to dynamically focus on the most relevant features across different views, while KAN provides a nonlinear feature representation capable of efficiently approximating arbitrary multivariate continuous functions, thereby capturing complex relationships and latent patterns within the data. Experimental results on four datasets containing sensitive attributes demonstrate that DFMVC-AKAN significantly improves fairness and clustering performance compared to state-of-the-art methods.