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 Dong${}^1$, Xiaolin Zheng${}^{1\ast }$, Ruixun Zhang${}^2$, Yan Wang${}^3$
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。