Multi-view Feature Selection for Recommender System

What is it about?

This research is about feature selection for recommender system. Feature selection is a technique to select key features. MvFS employs a multi-view network consisting of multiple sub-network, which promotes more balanced feature selection while mitigating bias toward dominant patterns.

Featured Image

Photo by Benjamin Dada on Unsplash

Photo by Benjamin Dada on Unsplash

Why is it important?

Feeding all features into the model often leads to suboptimal. Also, each instance has different important features. In this respect, MvFS allows balanced feature selection for each instance mitigating bias toward dominant patterns.