Multi-Metric AutoRec for High Dimensional and Sparse User Behavior Data Prediction

TL;DR

This paper introduces a multi-metric AutoRec model that combines various loss functions and regularizations across different metric spaces to better handle heterogeneous and sparse user behavior data in recommender systems.

Contribution

The paper proposes a novel multi-metric AutoRec model that aggregates multiple metric-based variants to improve prediction performance on sparse, high-dimensional user data.

Findings

MMA outperforms seven state-of-the-art models on five real-world datasets.

Theoretical analysis confirms performance improvements.

Multi-metric approach enhances representation of user behavior data.

Abstract

User behavior data produced during interaction with massive items in the significant data era are generally heterogeneous and sparse, leaving the recommender system (RS) a large diversity of underlying patterns to excavate. Deep neural network-based models have reached the state-of-the-art benchmark of the RS owing to their fitting capabilities. However, prior works mainly focus on designing an intricate architecture with fixed loss function and regulation. These single-metric models provide limited performance when facing heterogeneous and sparse user behavior data. Motivated by this finding, we propose a multi-metric AutoRec (MMA) based on the representative AutoRec. The idea of the proposed MMA is mainly two-fold: 1) apply different $L_p$-norm on loss function and regularization to form different variant models in different metric spaces, and 2) aggregate these variant models. Thus, the proposed MMA enjoys the multi-metric orientation from a set of dispersed metric spaces, achieving a comprehensive representation of user data. Theoretical studies proved that the proposed MMA could attain performance improvement. The extensive experiment on five real-world datasets proves that MMA can outperform seven other state-of-the-art models in predicting unobserved user behavior data.