FM(factorization Machines)

《Factorization Machines》paper的阅读笔记,仅为了整理个人思路。

个人觉得FM的本质就是预测值=偏置+权重1单变量+权重2变量之间的相互作用。
偏置和权重都可以是标量,也可以是向量

下面是本人认为重要的文章内容摘抄与翻译,能力有限,水平不足,不喜请绕道。

一 FM的优点

- 能够估计SVM所不能的稀疏矩阵的参数
(FMs allow parameter estimation under very sparse data where SVMs fail)

- FM 具有线性复杂性(相当于SVM中的多项核),能够在原始数据中进行优化,无需像SVM一样依赖支持向量。
(FMs have linear complexity,can be optimized in the primal and do not rely on support vectors like SVMs)

- FM 具有一般性,能够适用于任何真实值的特征向量,能够模拟偏置MF,SVD++,PITF,FPMC等最先进的模型。
(FMs are a general predictor that can work with any real valued feature vector.In contrast to this ,other state-of-the-art factorization models work only on very restricted input data.We will show that just by defining the feature vectors of the input data,FMs can mimic state-of-the- art models like biased MF ,SVD++,PITF,or FPMC.)

二 FM模型的公式

y ^ ( x ) = w 0 + i = 1 n w i x i + i 1 n j = i + 1 n < v i , v j > x i x j \hat{y}(x) = w_0 +\sum_{i=1}^{n}w_ix_i + \sum_{i-1}^{n}\sum_{j=i+1}{n}<v_i,v_j>x_ix_j
w 0 R w_0 \in R , w R n w\in R^n , V R n k V\in R^{n*k} ,
<.,.>是大小为K的两个向量的点积, &lt; v i , v j &gt; = f = 1 k v i , f . v j , f &lt;v_i,v_j&gt; = \sum_{f=1}^{k}v_{i,f}.v_{j,f}

V中的行向量 v i v_i 代表的是有K个因子的第i个变量。
k N 0 + k \in N_{0}^{+} 是定义因子的超参。

(A row w i w_i within V describes the i i -th variable with k factors. k N 0 + k \in N_{0}^{+} is a hyperparameter that defines the dimensionality of the factorization)

自由度为2的FM能够捕捉单变量和变量之间相互作用。
(A 2-way FM(degree d = 2) captures all single and pairwise interactions between variables)

  • w 0 w_0 是全局变量
  • w i w_i 模拟第i个变量的strength(个人觉得其实就是权重,models the strength of the i-th variable)
  • w ^ i , j = &lt; v i , v j &gt; \hat w_{i,j} = &lt;v_i,v_j&gt; 模拟第i和第j个变量之间的相互作用。(个人觉得其实就是权重,models the interaction between the i-th and j-th variable)

三 FM模型的表达能力

假设K足够大,对于任何正定矩阵W,存在一个矩阵V满足 V . V t V.V_t 。也就是说,如果K的选择足够大,FM便能够表达任意的相互作用向量W。为了使模型具有更好的泛化能力,在稀疏数据集中,通常选在比较小的K,。

(It is well known that for any positive definite matrix W, there exists a matrix V such thta W = V . V t W=V.V^t provided that k k is large enough. Nevertheless, in sparse settings,typically a small k k shold be chosen because there is not engough data to estimate complex interactions W.Restricting K - and thus the expressiveness of the FM -leads to better generalization and thus improved interaction matrics under sparsity)

发布了113 篇原创文章 · 获赞 51 · 访问量 17万+

猜你喜欢

转载自blog.csdn.net/weixin_43055882/article/details/98049969