Train Once, Use Flexibly: A Modular Framework for Multi-Aspect Neural News Recommendation

TL;DR

This paper introduces MANNeR, a modular neural news recommendation framework that enables on-the-fly multi-aspect customization at inference time without retraining, outperforming existing models.

Contribution

MANNeR's novel modular design allows flexible, real-time multi-aspect customization in neural news recommendation, reducing retraining needs and improving performance.

Findings

MANNeR outperforms state-of-the-art NNRs in standard and customized tasks.

The framework is robust across different languages and domains.

It effectively combines aspect-specific similarity scores for ranking.

Abstract

Recent neural news recommenders (NNRs) extend content-based recommendation (1) by aligning additional aspects (e.g., topic, sentiment) between candidate news and user history or (2) by diversifying recommendations w.r.t. these aspects. This customization is achieved by ``hardcoding`` additional constraints into the NNR's architecture and/or training objectives: any change in the desired recommendation behavior thus requires retraining the model with a modified objective. This impedes widespread adoption of multi-aspect news recommenders. In this work, we introduce MANNeR, a modular framework for multi-aspect neural news recommendation that supports on-the-fly customization over individual aspects at inference time. With metric-based learning as its backbone, MANNeR learns aspect-specialized news encoders and then flexibly and linearly combines the resulting aspect-specific similarity scores into different ranking functions, alleviating the need for ranking function-specific retraining of the model. Extensive experimental results show that MANNeR consistently outperforms state-of-the-art NNRs on both standard content-based recommendation and single- and multi-aspect customization. Lastly, we validate that MANNeR's aspect-customization module is robust to language and domain transfer.