本文策略：基于FM的框架，把user，item，content组成feature vector；然后把FM中的<xi,xj>的feature representation real-valued element 变成+1或-1（即discrete）。这么做的好处是，节省存储空间（甚至同时不影响或者提升推荐准确度）
以上的核心是改变FM中feature 之间的关系矩阵X，最简单的方法是把大于0的元素变成+1，把小于0的元素变成-1，但缺点是影响推荐性能。所以作者采取了一些方法解决了这个问题（本质上也是手动把某些元素改变+1或-1）。
技术路线：DCF （Discrete Collaborative Filtering） -> DCMF （Discrete Content-aware Matrix Factorization） -> DFM （Discrete Factorization Machine）
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| Discrete Factorization Machines for Fast Feature-based Recommendation | |||||||||||
| 文献作者 | Han Liu; Xiangnan He | ||||||||||
| 文献发表年限 | 2018 | ||||||||||
| 文献关键字 | |||||||||||
| FM; discrete; content-based | |||||||||||
| 摘要描述 | |||||||||||
| User and item features of side information are crucial for accurate recommendation. However, the large number of feature dimensions, e.g., usually larger than 107, results in expensive storage and computational cost. This prohibits fast recommendation especially on mobile applications where the computational resource is very limited. In this paper, we develop a generic feature-based recommendation model, called Discrete Factorization Machine (DFM), for fast and accurate recommendation. DFM binarizes the real-valued model param- eters (e.g., float32) of every feature embedding into binary codes (e.g., boolean), and thus supports effi- cient storage and fast user-item score computation. To avoid the severe quantization loss of the binarization, we propose a convergent updating rule that resolves the challenging discrete optimization of DFM. Through extensive experiments on two real-world datasets, we show that 1) DFM consistently outperforms state-of-the-art binarized recommendation models, and 2) DFM shows very competitive performance compared to its real-valued version (FM), demonstrating the minimized quantization loss. | |||||||||||
