User-Item协同自回归模型的协同过滤

为什么80%的码农都做不了架构师？>>>   

Besides the success on object recognition, machine translation and system control in games, (deep) neural networks have achieved state-of-the-art results in collaborative filtering (CF) recently. Previous neural approaches for CF are either user-based or item-based, which cannot leverage all relevant information explicitly. We propose CF-UIcA, a neural co-autoregressive model for CF tasks, which exploit the structural autoregressiveness in the domains of both users and items. Furthermore, we separate the inherent dependence in this structure under a natural assumption and develop an efficient stochastic learning algorithm to handle large scale datasets. We evaluate CF-UIcA on two popular benchmarks: MovieLens 1M and Netflix, and achieve state-of-the-art predictive performance, which demonstrates the effectiveness of CF-UIcA.

神经网络在物体识别，机器翻译中取得了成功。

之前的Neural CF方法(user-based or item-based)不能明显的平衡相关信息。这里提出了一种CF-UIc方法。

CF中两大关联：User-User Correlations (UUCs) and Item-Item Correlations (IICs)

隐藏变量模型：Matrix Factorization(MF) and neural network based models

MF methods take both UUCs and IICs in count implicitly as a prediction is the inner product of the latent vectors of the corresponding user and item.

两类NN-based协同过滤：RBM-CF和CF-NADE 只考虑UUC和IIC中的一个

而CF-UIcA同时基于UUC和IIC预测推荐结果

上图中，绿色/黄色/灰色分别对应喜欢/不喜欢/未评价

(a)Predicting with a single User-User Correlation.
(b) Predicting with a single Item-Item Correlation.
(c) Predicting with multiple User-User Correlations.
(d) Predicting with multiple Item-Item Correlations.
1.问题的形式化与符号化
(user, item, rating)三元组记为(i,j,Rij),评分范围1-K

假定系统有D个三元组，D<<N*M

σ是(1,2,..,n)的排列

2.数学模型

UUC和IIC的条件模型：

其中
隐藏层

转载于:https://my.oschina.net/lfxu/blog/831774