Context-Aware Hypergraph Construction for Robust Spectral Clustering

Abstract

Spectral clustering is a powerful tool for unsupervised data analysis. In this paper, we propose a context-aware hypergraph similarity measure (CAHSM), which leads to robust spectral clustering in the case of noisy data. We construct three types of hypergraph---the pairwise hypergraph, the k-nearest-neighbor (kNN) hypergraph, and the high-order over-clustering hypergraph. The pairwise hypergraph captures the pairwise similarity of data points; the kNN hypergraph captures the neighborhood of each point; and the clustering hypergraph encodes high-order contexts within the dataset. By combining the affinity information from these three hypergraphs, the CAHSM algorithm is able to explore the intrinsic topological information of the dataset. Therefore, data clustering using CAHSM tends to be more robust. Considering the intra-cluster compactness and the inter-cluster separability of vertices, we further design a discriminative hypergraph partitioning criterion (DHPC). Using both CAHSM and DHPC, a robust spectral clustering algorithm is developed. Theoretical analysis and experimental evaluation demonstrate the effectiveness and robustness of the proposed algorithm.Comment: 10 pages. Appearing in IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING: http://doi.ieeecomputersociety.org/10.1109/TKDE.2013.12

Fusing $${\mathcal {R}}$$ R Features and Local Features with Context-Aware Kernels for Action Recognition

“…Zhang et al [58] construct a feature correlation hypergraph to model high order relations among multimodal features for object recognition in images. Li et al [20] construct three types of hypergraphs: the pairwise hypergraph, the k nearest neighbor (kNN) hypergraph, and the high order over-clustering hypergraph. They further design a discriminative hypergraph partitioning criterion for face recognition and handwritten digit recogniton.…”

“…Each image is taken as a "centroid" vertex and a hyperedge is formed by a centroid and its k nearest neighbors [20]. Huang et al [10] assign each vertex to a hyperedge in a probabilistic way and propose a probabilistic hypergraph.…”

A Robust Battery Grouping Method Based on a Characteristic Distribution Model

“…Unlike traditional clustering algorithms, spectral clustering methods apply spectral graph theory to solve the non-convex sphere of sample spaces, and can achieve a global optimal solution without any assumptions on the structure of data. Hence, spectral clustering has achieved outstanding performance in many areas [23][24][25] and become one of the hottest topics in clustering.…”

“…As shown in the Figure 4a, the curves of the batteries are divided into five clusters, but it is impossible to decide which m batteries should be grouped into the same pack. Then, another widely used clustering algorithm, the spectral clustering algorithm [21,24], is also applied. As shown in Figure 4b, batteries can also be divided into five clusters, but it is again still impossible to decide which m batteries should be grouped into the same pack.…”

“…As shown in Figure 4b, batteries can also be divided into five clusters, but it is again still impossible to decide which m batteries should be grouped into the same pack. [21,24]. Note that the battery discharge curves can be divided into several clusters (represented by different colors), but it is impossible to decide which m batteries should be grouped into the same pack.…”