Adaptive Latent Factor Analysis via Generalized Momentum-Incorporated Particle Swarm Optimization

TL;DR

This paper introduces a novel GM-PSO algorithm that enhances hyper-parameter self-adaptation in latent factor analysis, improving accuracy in high-dimensional incomplete data scenarios.

Contribution

It proposes a generalized-momentum-incorporated PSO method to prevent premature convergence and improve hyper-parameter self-adaptation in LFA models.

Findings

GMPL outperforms standard methods in prediction accuracy.

The approach effectively avoids premature convergence.

Experimental results validate improved performance on industrial datasets.

Abstract

Stochastic gradient descent (SGD) algorithm is an effective learning strategy to build a latent factor analysis (LFA) model on a high-dimensional and incomplete (HDI) matrix. A particle swarm optimization (PSO) algorithm is commonly adopted to make an SGD-based LFA model's hyper-parameters, i.e, learning rate and regularization coefficient, self-adaptation. However, a standard PSO algorithm may suffer from accuracy loss caused by premature convergence. To address this issue, this paper incorporates more historical information into each particle's evolutionary process for avoiding premature convergence following the principle of a generalized-momentum (GM) method, thereby innovatively achieving a novel GM-incorporated PSO (GM-PSO). With it, a GM-PSO-based LFA (GMPL) model is further achieved to implement efficient self-adaptation of hyper-parameters. The experimental results on three HDI matrices demonstrate that the GMPL model achieves a higher prediction accuracy for missing data estimation in industrial applications.