LibRec 精选：混合推荐的论文综述

LibRec 精选

LibRec智能推荐 第 24 期（至2019.1.25），更新 5 篇精彩讨论内容。

生命的历程就像是写在水上的字，顺流而下，想回头寻找的时候总是失去了痕迹。-- 林清玄 《境明，千里皆明》

1

【图书】Practical Recommender Systems: https://t.co/vL2RlduV1G，源码: https://github.com/practical-recommender-systems/moviegeek

2

【课程】深度学习课程的PPT和笔记：

+ 主页: https://m2dsupsdlclass.github.io/lectures-labs/

+ 源码: https://github.com/m2dsupsdlclass/lectures-labs

---

1. Hybrid Recommender Systems: A Systematic Literature Review

Erion Çano, Maurizio Morisio

https://arxiv.org/abs/1901.03888v1

Hybrid recommender systems combine two or more recommendation strategies in different ways to benefit from their complementary advantages. This systematic literature review presents the state of the art in hybrid recommender systems of the last decade. We also explore the hybridization classes each hybrid recommender belongs to, the application domains, the evaluation process and proposed future research directions.

2. Using offline metrics and user behavior analysis to combine multiple systems for music recommendation

Andres Ferraro, Dmitry Bogdanov, Kyumin Choi, Xavier Serra

https://arxiv.org/abs/1901.02296v1

Hybrid recommendation approaches are commonly used to improve some of those metrics by combining different systems. In this work we focus on music recommendation and propose a new way to improve recommendations, with respect to a desired metric of choice, by combining multiple systems for each user individually based on their expected performance. As a proof of concept, we conduct experiments combining two recommendation systems, a Matrix Factorization model and a popularity-based recommender.

3. Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks

Zenan Ling, Haotian Ma, Yu Yang, Robert C. Qiu, Song-Chun Zhu, Quanshi Zhang

https://arxiv.org/abs/1901.02184v1

In this paper, we propose to disentangle and interpret contextual effects that are encoded in a pre-trained deep neural network. We use our method to explain the gaming strategy of the alphaGo Zero model. Explaining the logic of the alphaGo Zero model is a typical application.