MvFS: Multi-view Feature Selection for Recommender System

TL;DR

This paper introduces MvFS, a multi-view feature selection method for recommender systems that improves the selection of informative features by reducing bias towards dominant patterns, leading to better performance.

Contribution

The paper proposes a novel multi-view network approach for feature selection that mitigates bias and enhances the effectiveness of feature importance measurement in recommender systems.

Findings

MvFS outperforms state-of-the-art baselines on real-world datasets.

It effectively reduces bias towards major features.

Experimental results validate the improved feature selection quality.

Abstract

Feature selection, which is a technique to select key features in recommender systems, has received increasing research attention. Recently, Adaptive Feature Selection (AdaFS) has shown remarkable performance by adaptively selecting features for each data instance, considering that the importance of a given feature field can vary significantly across data. However, this method still has limitations in that its selection process could be easily biased to major features that frequently occur. To address these problems, we propose Multi-view Feature Selection (MvFS), which selects informative features for each instance more effectively. Most importantly, MvFS employs a multi-view network consisting of multiple sub-networks, each of which learns to measure the feature importance of a part of data with different feature patterns. By doing so, MvFS mitigates the bias problem towards dominant patterns and promotes a more balanced feature selection process. Moreover, MvFS adopts an effective importance score modeling strategy which is applied independently to each field without incurring dependency among features. Experimental results on real-world datasets demonstrate the effectiveness of MvFS compared to state-of-the-art baselines.