An ADMM-Incorporated Latent Factorization of Tensors Method for QoS Prediction

TL;DR

This paper introduces an ADMM-based tensor factorization method that improves QoS prediction by enhancing convergence speed and outlier resilience, effectively capturing temporal patterns in high-dimensional sparse data.

Contribution

It proposes a novel ADMM-incorporated nonnegative tensor factorization model that addresses convergence issues and outlier effects in QoS prediction tasks.

Findings

Faster convergence compared to existing models

Improved prediction accuracy on QoS datasets

Enhanced robustness to outliers

Abstract

As the Internet developed rapidly, it is important to choose suitable web services from a wide range of candidates. Quality of service (QoS) describes the performance of a web service dynamically with respect to the service requested by the service consumer. Moreover, the latent factorization of tenors (LFT) is very effective for discovering temporal patterns in high dimensional and sparse (HiDS) tensors. However, current LFT models suffer from a low convergence rate and rarely account for the effects of outliers. To address the above problems, this paper proposes an Alternating direction method of multipliers (ADMM)-based Outlier-Resilient Nonnegative Latent-factorization of Tensors model. We maintain the non-negativity of the model by constructing an augmented Lagrangian function with the ADMM optimization framework. In addition, the Cauchy function is taken as the metric function to reduce the impact on the model training. The empirical work on two dynamic QoS datasets shows that the proposed method has faster convergence and better performance on prediction accuracy.