PRECISE: Pre-training Sequential Recommenders with Collaborative and Semantic Information

TL;DR

PRECISE is a novel pre-training framework for sequential recommendation that combines collaborative and semantic information to better capture user interests across multiple scenarios, improving performance especially for long-tail and cold-start items.

Contribution

It introduces a new pre-training method that integrates collaborative signals with semantic information and models comprehensive user interests for diverse recommendation scenarios.

Findings

Achieves superior performance on public datasets.

Effectively transfers user interests to target scenarios.

Handles long-tail and cold-start items well.

Abstract

Real-world recommendation systems commonly offer diverse content scenarios for users to interact with. Considering the enormous number of users in industrial platforms, it is infeasible to utilize a single unified recommendation model to meet the requirements of all scenarios. Usually, separate recommendation pipelines are established for each distinct scenario. This practice leads to challenges in comprehensively grasping users' interests. Recent research endeavors have been made to tackle this problem by pre-training models to encapsulate the overall interests of users. Traditional pre-trained recommendation models mainly capture user interests by leveraging collaborative signals. Nevertheless, a prevalent drawback of these systems is their incapacity to handle long-tail items and cold-start scenarios. With the recent advent of large language models, there has been a significant increase in research efforts focused on exploiting LLMs to extract semantic information for users and items. However, text-based recommendations highly rely on elaborate feature engineering and frequently fail to capture collaborative similarities. To overcome these limitations, we propose a novel pre-training framework for sequential recommendation, termed PRECISE. This framework combines collaborative signals with semantic information. Moreover, PRECISE employs a learning framework that initially models users' comprehensive interests across all recommendation scenarios and subsequently concentrates on the specific interests of target-scene behaviors. We demonstrate that PRECISE precisely captures the entire range of user interests and effectively transfers them to the target interests. Empirical findings reveal that the PRECISE framework attains outstanding performance on both public and industrial datasets.