本文中的Multi-Channel可以理解为cross-domain.
本文的核心：
（1）从raw feature到learned representation based on NN （主要是content based 的feature 以及ID 没有用到历史点击的item/news，点击行为在objective function时才考虑到）
（2）为不同的用户融合不同channel下学出的user representation， based on attention models
注意：
（1）在NN的结构中，从input到output到过程中，有一点值得学习：自动学出“几层”结构，把不同层数的结构并行的放到一起，再他们各自的结构构成最终的output；
（2）本文在学习user representation时直接用的content information；但是在考虑loss时（function objection），才考虑的用户点击行为。这与我们不考虑content，只考虑用户行为上有一点区别。我们会用点击的item embedding去表达user representation.
思考：
我们的新工作跟这篇的区别（仅仅是这篇没有考虑long-term and short-term？）
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| Towards Better Representation Learning for Personalized News Recommendations: A Multi-Channel Deep Fusion Approach | |||||||||||
| 文献作者 | Jianxun Lian | ||||||||||
| 文献发表年限 | 2018 | ||||||||||
| 文献关键字 | |||||||||||
| cross-domain; NN; attention model; attentive model；NSVD; 用点击的item embedding 去表达user representation | |||||||||||
| 摘要描述 | |||||||||||
| Millions of news articles emerge every day. How to provide personalized news recommendations has become a critical task for service providers. In the past few decades, latent factor models has been widely used for building recommender systems (RSs). With the remarkable success of deep learn- ing techniques, especially in visual computing and natural language understanding, more and more researchers, have been trying to leverage deep neural networks to learn latent representations for advanced RSs. Following mainstream deep learning- based RSs, we propose a novel deep fusion model (DFM), which aims to improve the representation learning abilities in deep RSs and can be used for both candidate retrieval and item re-ranking. There are two key components in our DFM approach, namely an inception module and an attention mechanism. The inception module improves the plain multi-layer network via leveraging of various levels of interaction simultaneously, while the attention mechanism merges latent representations learnt from different channels in a customized fashion. We conduct extensive experiments on a commercial news reading dataset, and the results demonstrate that the proposed DFM is superior to several state-of-the-art models. | |||||||||||
