Tiny-NewsRec: Efficient and Effective PLM-based News Recommendation

by   Yang Yu, et al.

Personalized news recommendation has been widely adopted to improve user experience. Recently, pre-trained language models (PLMs) have demonstrated the great capability of natural language understanding and the potential of improving news modeling for news recommendation. However, existing PLMs are usually pre-trained on general corpus such as BookCorpus and Wikipedia, which have some gaps with the news domain. Directly finetuning PLMs with the news recommendation task may be sub-optimal for news understanding. Besides, PLMs usually contain a large volume of parameters and have high computational overhead, which imposes a great burden on the low-latency online services. In this paper, we propose Tiny-NewsRec, which can improve both the effectiveness and the efficiency of PLM-based news recommendation. In order to reduce the domain gap between general corpora and the news data, we propose a self-supervised domain-specific post-training method to adapt the generally pre-trained language models to the news domain with the task of news title and news body matching. To improve the efficiency of PLM-based news recommendation while maintaining the performance, we propose a two-stage knowledge distillation method. In the first stage, we use the domain-specific teacher PLM to guide the student model for news semantic modeling. In the second stage, we use a multi-teacher knowledge distillation framework to transfer the comprehensive knowledge from a set of teacher models finetuned for news recommendation to the student. Experiments on two real-world datasets show that our methods can achieve better performance in news recommendation with smaller models.


page 1

page 2

page 3

page 4


NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application

Pre-trained language models (PLMs) like BERT have made great progress in...

Empowering News Recommendation with Pre-trained Language Models

Personalized news recommendation is an essential technique for online ne...

MergeDistill: Merging Pre-trained Language Models using Distillation

Pre-trained multilingual language models (LMs) have achieved state-of-th...

HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation

User interest modeling is critical for personalized news recommendation....

Prompt Learning for News Recommendation

Some recent news recommendation (NR) methods introduce a Pre-trained Lan...

GateFormer: Speeding Up News Feed Recommendation with Input Gated Transformers

News feed recommendation is an important web service. In recent years, p...

TrNews: Heterogeneous User-Interest Transfer Learning for News Recommendation

We investigate how to solve the cross-corpus news recommendation for uns...

Please sign up or login with your details

Forgot password? Click here to reset