NS4AR: A new, focused on sampling areas sampling method in graphical recommendation Systems

TL;DR

This paper introduces NS4AR, a focused sampling method for graphical recommender systems that improves negative sampling by dividing sample regions and weighting them with AdaSim, along with a subset selection model.

Contribution

The paper proposes a novel sampling approach, NS4AR, that enhances negative sampling in graphical recommender systems through regional division and weighted sampling.

Findings

Improved negative sampling quality in recommender systems.

Enhanced recommendation accuracy with the proposed sampling method.

Effective subset selection reduces negative sample volume.

Abstract

The effectiveness of graphical recommender system depends on the quantity and quality of negative sampling. This paper selects some typical recommender system models, as well as some latest negative sampling strategies on the models as baseline. Based on typical graphical recommender model, we divide sample region into assigned-n areas and use AdaSim to give different weight to these areas to form positive set and negative set. Because of the volume and significance of negative items, we also proposed a subset selection model to narrow the core negative samples.