Deep Matrix Factorization with Adaptive Weights for Multi-View Clustering
This work addresses multi-view clustering challenges for unsupervised learning applications, representing an incremental improvement over existing methods.
The paper tackled the lack of effective feature selection and reliance on empirical hyperparameters in deep matrix factorization for multi-view clustering by introducing DMFAW, which incorporates adaptive weights and a late fusion approach, achieving improved clustering performance on benchmark datasets.
Recently, deep matrix factorization has been established as a powerful model for unsupervised tasks, achieving promising results, especially for multi-view clustering. However, existing methods often lack effective feature selection mechanisms and rely on empirical hyperparameter selection. To address these issues, we introduce a novel Deep Matrix Factorization with Adaptive Weights for Multi-View Clustering (DMFAW). Our method simultaneously incorporates feature selection and generates local partitions, enhancing clustering results. Notably, the features weights are controlled and adjusted by a parameter that is dynamically updated using Control Theory inspired mechanism, which not only improves the model's stability and adaptability to diverse datasets but also accelerates convergence. A late fusion approach is then proposed to align the weighted local partitions with the consensus partition. Finally, the optimization problem is solved via an alternating optimization algorithm with theoretically guaranteed convergence. Extensive experiments on benchmark datasets highlight that DMFAW outperforms state-of-the-art methods in terms of clustering performance.