推荐系统,对于我们来说并不陌生,可以说无处不在。抖音的视频推荐让我们欲罢不能,淘宝的猜你喜欢令大家流连忘返,网易云的每日歌单使我们沉浸其中。可见,推荐技术已经成为了业界的流量担当、变现神器,也成为了我们的生活小助手,渗透到生活的各个方面。
推荐系统的核心是推荐算法,其通过利用用户对项目的行为数据、用户画像以及物品属性来构建推荐模型,进而对用户的未来行为进行预测。
推荐系统根据不同的分类维度可进行多种分类,以下进行举例介绍。
- 根据产品的存在形式可以分为:首页推荐、热门推荐和相关推荐等。
- 根据推荐技术的不同分为:基于内容的推荐、基于协同过滤的推荐、基于混合的推荐。
- 根据利用的信息不同可分为:协同过滤推荐、社会化推荐、兴趣点推荐、知识图推荐以及标签推荐等。
- 根据推荐任务不同可分为:评分预测和项目排序。
- 根据模型所利用假设不同分为:以KNN为代表的非训练的方法,以MF为代表的传统机器学习方法,以及以Wide&Deep模型为代表的深度学习推荐等。
可见推荐的形式以及种类繁多,对于刚入门的同学来说有点头疼。那么如何才能入门呢,相信最好的办法是阅读相关的综述文章(当然最好是有一定的数学基础以及背景知识)。因此本文的作用起到综述索引的效果,我也把她叫做推荐系统综述的综述(Surveys on Survey on Recommendation),将对25篇推荐系统综述归类为15种类别,希望能够对大家有一个整体的概念。然后便是选择其中一个具体细分领域进行深挖,成为该领域的佼佼者。
推荐系统综述
- Adomavicius et al. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE TKDE, 2005.
- Zhu et al. Research Commentary on Recommendations with Side Information: A Survey and Research Directions. Electron. Commer. Res. Appl., 2019
协同过滤综述
- Su et al. A survey of collaborative filtering techniques. Advances in artificial intelligence, 2009.
- Cacheda et al. Comparison of collaborative filtering algorithms: Limitations of current techniques and proposals for scalable, high-performance recommender systems. ACM TWEB, 2011.
- Shi et al. Collaborative filtering beyond the user-item matrix: A survey of the state of the art and future challenges. ACM COMPUT SURV, 2014.
- Efthalia et al. Parallel and Distributed Collaborative Filtering: A Survey. Comput. Surv., 2016.
混合推荐综述
- Burke et al. Hybrid Recommender Systems: Survey and Experiments. USER MODEL USER-ADAP, 2002.
标签推荐综述
- Zhang et al. Tag-aware recommender systems: a state-of-the-art survey. J COMPUT SCI TECHNOL, 2011.
社会化推荐综述
- Tang et al. Social recommendation: a review. SNAM, 2013.
- Yang et al. A survey of collaborative filtering based social recommender systems. COMPUT COMMUN, 2014.
- Xu et al. Social networking meets recommender systems: survey. Int.J.Social Network Mining, 2015.
- Liu et al. Survey of matrix factorization based recommendation methods by integrating social information. Journal of Software, 2018.
文本推荐综述
- Chen et al. Recommender systems based on user reviews: the state of the art. USER MODEL USER-ADAP, 2015.
兴趣点推荐综述
- Yu et al. A survey of point-of-interest recommendation in location-based social networks. In Workshops at AAAI, 2015.
跨域推荐综述
- Muhammad et al. Cross Domain Recommender Systems: A Systematic Literature Review. ACM Comput. Surv, 2017.
序列推荐综述
- Massimo et al. Sequence-Aware Recommender Systems. ACM Comput. Surv, 2018.
- Shoujin et al. Sequential Recommender Systems: Challenges, Progress and Prospects. IJCAI, 2019.
会话推荐综述
- Shoujin et al. A Survey on Session-based Recommender Systems. arXiv, 2019.
可解释推荐综述
- Zhang et al. Explainable Recommendation: A Survey and New Perspectives. Found. Trends Inf. Retr., 2020.
对话推荐系统综述
- Dietmar et al. A Survey on Conversational Recommender Systems. arXiv, 2020.
知识图推荐综述
- Qingyu et al. A Survey on Knowledge Graph-Based Recommender Systems. arXiv, 2020.
组推荐综述
- Sriharsha et al. A Survey on Group Recommender Systems. J. Intell. Inf. Syst., 2020
深度学习推荐综述
- Singhal et al. Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works. arXiv, 2017.
- Zhang et al. Deep learning based recommender system: A survey and new perspectives. ACM Comput.Surv, 2018.
- Batmaz et al. A review on deep learning for recommender systems: challenges and remedies. Artificial Intelligence Review, 2018.
更多论文参考:https://github.com/hongleizhang/RSPapers,欢迎Star。
当你看到这的时候,相信已经对某一篇或者多篇综述文章跃跃欲看了,别着急,走进后台回复【综述】即可打包享用。另外,若想一起交流推荐系统相关知识,欢迎进群。
推荐阅读
本文暂时没有评论,来添加一个吧(●'◡'●)