Rethinking negative sampling in content-based news recommendation

TL;DR

This paper introduces a novel negative sampling technique for content-based news recommendation systems that enhances accuracy, reduces model complexity, accelerates training, and supports decentralization for better privacy and scalability.

Contribution

The study proposes a new negative sampling method that improves accuracy and decentralization in news recommendation models, addressing complexity and training speed issues.

Findings

Competitive accuracy with state-of-the-art models

Reduced model complexity and faster training

Enhanced privacy and scalability through decentralization

Abstract

News recommender systems are hindered by the brief lifespan of articles, as they undergo rapid relevance decay. Recent studies have demonstrated the potential of content-based neural techniques in tackling this problem. However, these models often involve complex neural architectures and often lack consideration for negative examples. In this study, we posit that the careful sampling of negative examples has a big impact on the model's outcome. We devise a negative sampling technique that not only improves the accuracy of the model but also facilitates the decentralization of the recommendation system. The experimental results obtained using the MIND dataset demonstrate that the accuracy of the method under consideration can compete with that of State-of-the-Art models. The utilization of the sampling technique is essential in reducing model complexity and accelerating the training process, while maintaining a high level of accuracy. Finally, we discuss how decentralized models can help improve privacy and scalability.