DRSLF: Double Regularized Second-Order Low-Rank Representation for Web Service QoS Prediction

TL;DR

This paper introduces DRSLF, a novel model that improves web service QoS prediction by combining double regularization and second-order optimization, leading to more accurate and robust low-rank representations.

Contribution

The paper proposes a double regularized second-order latent factor model that enhances QoS prediction accuracy by integrating L1/L2 regularization and second-order information.

Findings

DRSLF outperforms baseline models in real-world datasets.

Incorporating second-order information improves convergence and accuracy.

Double regularization enhances low-rank representation capability.

Abstract

Quality-of-Service (QoS) data plays a crucial role in cloud service selection. Since users cannot access all services, QoS can be represented by a high-dimensional and incomplete (HDI) matrix. Latent factor analysis (LFA) models have been proven effective as low-rank representation techniques for addressing this issue. However, most LFA models rely on first-order optimizers and use L2-norm regularization, which can lead to lower QoS prediction accuracy. To address this issue, this paper proposes a double regularized second-order latent factor (DRSLF) model with two key ideas: a) integrating L1-norm and L2-norm regularization terms to enhance the low-rank representation performance; b) incorporating second-order information by calculating the Hessian-vector product in each conjugate gradient step. Experimental results on two real-world response-time QoS datasets demonstrate that DRSLF has a higher low-rank representation capability than two baselines.