Uncertainty-adjusted inductive matrix completion with Graph Neural Networks

• Main Authors: KASALICKY, Petr, LEDENT, Antoine, ALVES, Rodrigo
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: anomaly detection; graph neural network; matrix completion; uncertainty; Artificial Intelligence and Robotics; Numerical Analysis and Scientific Computing; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8258; https://ink.library.smu.edu.sg/context/sis_research/article/9261/viewcontent/Uncertainty_adjusted_IMC_GNN_av.pdf
• Institution: Singapore Management University

We propose a robust recommender systems model which performs matrix completion and a ratings-wise uncertainty estimation jointly. Whilst the prediction module is purely based on an implicit low-rank assumption imposed via nuclear norm regularization, our loss function is augmented by an uncertainty...