Skip to Main content Skip to Navigation
Conference papers

Fast & furious: accelerating weighted NMF using random projections

Abstract : Random projections have been successfully applied to accelerate Nonnegative Matrix Factorization (NMF). However, they are not suited to the case of missing entries in the matrix to factorize, which occurs in many actual problems with large data matrices. In this paper, we thus aim to solve this issue and we propose a novel framework to apply random projections in weighted NMF, where the weight models the confidence in the data. We experimentally show the proposed framework to significantly speed-up state-of-the-art NMF methods under some mild conditions.
Document type :
Conference papers
Complete list of metadata
Contributor : Matthieu Puigt <>
Submitted on : Saturday, June 8, 2019 - 3:52:57 PM
Last modification on : Tuesday, January 5, 2021 - 1:04:02 PM


  • HAL Id : hal-02151522, version 1



Farouk Yahaya, Matthieu Puigt, Gilles Delmaire, Gilles Roussel. Fast & furious: accelerating weighted NMF using random projections. Workshop on Low-Rank Models and Applications (LRMA), Sep 2019, Mons, Belgium. ⟨hal-02151522⟩



Record views