Pre-train and Fine-tune: Recommenders as Large Models

TL;DR

This paper proposes a novel fine-tuning approach for large pre-trained recommenders using an information-aware adaptive kernel, improving adaptability to user interest changes with successful large-scale deployment.

Contribution

It introduces an information-theoretic framework for fine-tuning recommenders and designs the IAK technique tailored for recommendation systems, with practical deployment insights.

Findings

IAK outperforms traditional fine-tuning methods in experiments.

The approach is interpretable and effective in large-scale online deployment.

Deployment on a billion-scale platform yielded significant business profits.

Abstract

In reality, users have different interests in different periods, regions, scenes, etc. Such changes in interest are so drastic that they are difficult to be captured by recommenders. Existing multi-domain learning can alleviate this problem. However, the structure of the industrial recommendation system is complex, the amount of data is huge, and the training cost is extremely high, so it is difficult to modify the structure of the industrial recommender and re-train it. To fill this gap, we consider recommenders as large pre-trained models and fine-tune them. We first propose the theory of the information bottleneck for fine-tuning and present an explanation for the fine-tuning technique in recommenders. To tailor for recommendation, we design an information-aware adaptive kernel (IAK) technique to fine-tune the pre-trained recommender. Specifically, we define fine-tuning as two phases: knowledge compression and knowledge matching and let the training stage of IAK explicitly approximate these two phases. Our proposed approach designed from the essence of fine-tuning is well interpretable. Extensive online and offline experiments show the superiority of our proposed method. Besides, we also share unique and important lessons we learned when deploying the method in a large-scale online platform. We also present the potential issues of fine-tuning techniques in recommendation systems and the corresponding solutions. The recommender with IAK technique has been deployed on the homepage of a billion-scale online food platform for several months and has yielded considerable profits in our business.