Parameter-less Auto-weighted multiple graph regularized Nonnegative Matrix Factorization for data representation

By Zhenqiu Shu, Xiaojun Wu, H. Fan, Pu Huang, Dong Wu, Cong Hu, Feiyue Ye. Knowledge-Based Systems, 2017

550 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Collaborative Filtering with Graph Information: Consistency and Scalable Methods (2015, methodology): “In the context of matrix factorization with graph structural information, [5] considered a graph regularized nonnegative matrix factorization framework and proposed a gradient descent based method to solve the problem.”
Deep Subspace Clustering Networks (2017, methodology): “Following [3], we down-sampled the images to 32 × 32.”
On Unifying Multi-view Self-Representations for Clustering by Tensor Multi-rank Minimization (2016, methodology): “Then, we can get Gf = bdfold { bdiag(Uf )bdiag(Sf,τ ′)bdiag(Vf )T } (43) and G = U ∗ S̃ ∗ VT (44) 0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.8 2 λ 0.6 0.65 0.7 0.75 0.8 0.85 0.9 0.95 1 A C C (a) ACC on Yale 0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.8 2 λ 0.65 0.7 0.75 0.8 0.85 0.9 0.95 1 N M I (b) NMI on Yale 0 0.2 ”