Self-weighting multi-view spectral clustering based on nuclear norm

Highlights：

• Considering that each view feature is inclined to explore specific properties, therefore, the proposed method assigns different weight for each view feature in the form of exponential flatten.

• An efficient alternative iteration algorithm is exploited to solve the proposed optimization problem. In addition, extensive experiments are conducted on four multi-view data sets without noises and one multi-view data set with“salt and pepper” noises to demonstrate the superiority of proposed SMSC_NN method.

摘要

•In order to implement clustering task, the proposed approach fully utilizes multiple view features to learn a consensus representation. Specifically, it makes the common consensus representation be close to each view initial affinity matrix as much as possible. Moreover, to capture principal components of different views, the nuclear norm is applied to the learned consensus representation.•Considering that each view feature is inclined to explore specific properties, therefore, the proposed method assigns different weight for each view feature in the form of exponential flatten.•An efficient alternative iteration algorithm is exploited to solve the proposed optimization problem. In addition, extensive experiments are conducted on four multi-view data sets without noises and one multi-view data set with“salt and pepper” noises to demonstrate the superiority of proposed SMSC_NN method.