Contrastive learning (CL) has shown its power in recommendation. However, most CL-based recommendation models build their CL tasks merely focusing on the user's aspects, ignoring the rich diverse information in items. In this work, we propose a novel Multi-granularity item-based contrastive learning (MicRec) framework for the matching stage (i.e., candidate generation) in recommendation, which systematically introduces multi-aspect item-related information to representation learning with CL. Specifically, we build three item-based CL tasks as a set of plug-and-play auxiliary objectives to capture item correlations in feature, semantic and session levels. The feature-level item CL aims to learn the fine-grained feature-level item correlations via items and their augmentations. The semantic-level item CL focuses on the coarse-grained semantic correlations between semantically related items. The session-level item CL highlights the global behavioral correlations of items from users' sequential behaviors in all sessions. In experiments, we conduct both offline and online evaluations on real-world datasets, where MicRec achieves significant improvements over competitive baselines. Moreover, we further verify the effectiveness of three CL tasks as well as the universality of MicRec on different matching models. The proposed MicRec is effective, efficient, universal, and easy to deploy, which has been deployed on a real-world recommendation system, affecting millions of users. The source code will be released in the future.

翻译：以 CL 为基础的大多数 CL 推荐模式建立其 CL 任务时只关注用户的方方面面,忽略了项目中丰富多样的信息。在这项工作中,我们提议为匹配阶段(即候选人生成)的匹配阶段(即候选人生成)建立一个基于多角度项目对比学习(MicRec)框架,系统地引入多层次项目相关信息,用于与 CL 学习。具体地说,我们建立三个基于项目的 CL 任务,作为一组插接和播放辅助目标,以捕捉功能、语义和会话层面的项目相关性。在实验中,我们通过项目及其增强来学习精细区分的基于特性的项目级对比性项目(MicRec ) 。语义级CL 侧重于与语义相关项目之间的粗糙的语义相关关系。 届会级项目CL 强调了所有会议中用户连续行为的全球行为相关性。 在实验中,我们进行离线和在线项目的相关性关联性项目 通过项目及其增强功能性基准值, 将进一步影响真实性基准值 。