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

Nithish Kannen, Yao Ma, Gerrit Van Den Burg, Jean Baptiste Faddoul


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.
Anthology ID:
2024.findings-emnlp.723
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12403–12418
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.723
DOI:
Bibkey:
Cite (ACL):
Nithish Kannen, Yao Ma, Gerrit Van Den Burg, and Jean Baptiste Faddoul. 2024. Efficient Pointwise-Pairwise Learning-to-Rank for News Recommendation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12403–12418, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Efficient Pointwise-Pairwise Learning-to-Rank for News Recommendation (Kannen et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.723.pdf