Efficient Pointwise-Pairwise Learning-to-Rank for News Recommendation

TL;DR

This paper introduces a scalable learning-to-rank framework combining pointwise and pairwise methods for news recommendation, leveraging pretrained language models to improve ranking accuracy and efficiency.

Contribution

The paper proposes a novel integrated framework that combines pointwise and pairwise learning-to-rank approaches with theoretical guarantees, enhancing news recommendation performance.

Findings

Outperforms state-of-the-art methods on MIND and Adressa datasets.

Provides theoretical analysis ensuring performance improvements.

Achieves a balance between computational efficiency and ranking effectiveness.

Abstract

News recommendation is a challenging task that involves personalization based on the interaction history and preferences of each user. Recent works have leveraged the power of pretrained language models (PLMs) to directly rank news items by using inference approaches that predominately fall into three categories: pointwise, pairwise, and listwise learning-to-rank. While pointwise methods offer linear inference complexity, they fail to capture crucial comparative information between items that is more effective for ranking tasks. Conversely, pairwise and listwise approaches excel at incorporating these comparisons but suffer from practical limitations: pairwise approaches are either computationally expensive or lack theoretical guarantees, and listwise methods often perform poorly in practice. In this paper, we propose a novel framework for PLM-based news recommendation that integrates both pointwise relevance prediction and pairwise comparisons in a scalable manner. We present a rigorous theoretical analysis of our framework, establishing conditions under which our approach guarantees improved performance. Extensive experiments show that our approach outperforms the state-of-the-art methods on the MIND and Adressa news recommendation datasets.