Matrix Decomposition on Graphs: A Simplified Functional View - Archive ouverte HAL
Communication Dans Un Congrès Année : 2022

Matrix Decomposition on Graphs: A Simplified Functional View

Résumé

We propose a simplified functional view of matrix decomposition problems on graphs such as geometric matrix completion. Our unifying framework is based on the key idea that using a reduced basis to represent functions on the product space is sufficient to recover a low rank matrix approximation even from a sparse signal. We validate our framework on several real and synthetic benchmarks where it either outperforms very competitive baselines or achieves competitive results at a fraction of the computational effort of prior work.
Fichier principal
Vignette du fichier
Matrix_Decomposition_on_Graphs_A_Simplified_Functional_View.pdf (969.25 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04479857 , version 1 (27-02-2024)

Identifiants

Citer

Abhishek Sharma, Maks Ovsjanikov. Matrix Decomposition on Graphs: A Simplified Functional View. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022, Singapore, France. pp.3358-3362, ⟨10.1109/ICASSP43922.2022.9746243⟩. ⟨hal-04479857⟩
12 Consultations
38 Téléchargements

Altmetric

Partager

More