16 December 2021 in IEEE Transactions on Multimedia
Multi-view clustering, which elegantly integrates information from multiple sources to reveal the intrinsic structure among data, is attracting increasing attention in the field of machine learning. Although good performance has been achieved by the existing methods, we observe that they have neglected the inherent local structure between the base kernels. This may cause adverse effects on clustering performance. In this paper, we propose a simple but effective late fusion multiple kernel clustering with local kernel alignment maximization algorithm (LF-MKC-LKA) to address the issue. Specifically, we first search the neighbors for each sample by finding the nearest k neighbors in the average kernel space and then get neighbor indicator matrix for each sample. With the help of neighbor indicator matrix, the local kernels for each view can be constructed subsequently, which preserve only the high-confidence local similarities for learning the intrinsic global manifold of data. Moreover, they can be used to preserve the block diagonal structure and boost the robustness against noise between the base kernels. We input the local kernels of each view into the kernel $k$ -means (KKM) algorithm and get the local basic partitions. Finally, we use the local basic partitions as late fusion input to design a three-step iterative algorithm. As demonstrated, the proposed LF-MKC-LKA is proved to be effective and efficient by a large number of experiments on $11$ multi-kernel benchmark datasets. A series of experiments are also designed to prove the fast convergence, excellent performance, robustness and low parameter sensitivity of the algorithm.
17 November 2022 in IEEE Transactions on Neural Networks and Learning Systems
Deep clustering, which can elegantly exploit data representation to seek a partition of the samples, has attracted intensive attention. Recently, combining auto-encoder (AE) with graph neural networks (GNNs) has accomplished excellent performance by introducing structural information implied among data in clustering tasks. However, we observe that there are some limitations of most existing works: 1) in practical graph datasets, there exist some noisy or inaccurate connections among nodes, which would confuse network learning and cause biased representations, thus leading to unsatisfied clustering performance; 2) lacking dynamic information fusion module to carefully combine and refine the node attributes and the graph structural information to learn more consistent representations; and 3) failing to exploit the two separated views’ information for generating a more robust target distribution. To solve these problems, we propose a novel method termed deep fusion clustering network with reliable structure preservation (DFCN-RSP). Specifically, the random walk mechanism is introduced to boost the reliability of the original graph structure by measuring localized structure similarities among nodes. It can simultaneously filter out noisy connections and supplement reliable connections in the original graph. Moreover, we provide a transformer-based graph auto-encoder (TGAE) that can use a self-attention mechanism with the localized structure similarity information to fine-tune the fused topology structure among nodes layer by layer. Furthermore, we provide a dynamic cross-modality fusion strategy to combine the representations learned from both TGAE and AE. Also, we design a triplet self-supervision strategy and a target distribution generation measure to explore the cross-modality information. The experimental results on five public benchmark datasets reflect that DFCN-RSP is more competitive than the state-of-the-art deep clustering algorithms. The corresponding code is available at https://github.com/gongleii/DFCN-RSP.