1 简介
论文:用于统一一般推荐和序列推荐的循环协同过滤
Recurrent Collaborative Filtering for Unifying General and Sequential Recommender
出版:Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18)
作者:Disheng Dong1^11, Xiaolin Zheng1∗^{1*}1∗, Ruixun Zhang2^22, Yan Wang3^33
1 Zhejiang University
2 MIT Laboratory for Financial Engineering
3 Macquarie University
2 摘要
作者将推荐分为一般推荐和序列推荐。
一般推荐:General recommender focuses on modeling the general user preferences, ignoring the sequential patterns in user behaviors。
序列推荐:Sequential recommender focuses on exploring the item-to-item sequential relations, failing to model the global user preferences.
已有的工作:In addition, better recommendation performance has recently been achieved by adopting an approach to combining them. 此外,最近通过采用组合它们的方法实现了更好的推荐性能。
缺点:However, the existing approaches are unable to solve both tasks in a unified way and cannot capture the whole historical sequential information.然而,现有方法无法统一解决这两个任务,也无法捕获整个历史序列信息。
方案: In this paper, we propose a recommendation model named Recurrent Collaborative Filtering (RCF), which unifies both paradigms within a single model. Specifically, we combine recurrent neural network (the sequential recommender part) and matrix factorization model (the general recommender part) in a multi-task learning framework, where we perform joint optimization with shared model parameters enforcing the two parts to regularize each other. 在本文中,我们提出了一种名为循环协作过滤(RCF)的推荐模型,它将两种范式统一在一个模型中。 具体来说,我们将循环神经网络(序列推荐部分)和矩阵分解模型(一般推荐部分)结合在一个多任务学习框架中,我们使用共享模型参数执行联合优化,强制这两个部分相互规范。