...
首页> 外文期刊>Knowledge-Based Systems >Matrix factorization for recommendation with explicit and implicit feedback
【24h】

Matrix factorization for recommendation with explicit and implicit feedback

机译:矩阵分解以提供显式和隐式反馈的推荐

获取原文
获取原文并翻译 | 示例
           

摘要

Matrix factorization (MF) methods have proven as efficient and scalable approaches for collaborative filtering problems. Numerous existing MF methods rely heavily on explicit feedback. Typically, these data types may be extremely sparse; therefore, these methods can perform poorly. In order to address these challenges, we propose a latent factor model based on probabilistic MF, by incorporating implicit feedback as complementary information. Specifically, the explicit and implicit feedback matrices are decomposed into a shared subspace simultaneously. Then, the latent factor vectors are jointly optimized using a gradient descent algorithm. The experimental results using the MovieLens datasets demonstrate that the proposed algorithm outperforms the baselines.
机译:事实证明,矩阵分解(MF)方法是解决协作过滤问题的有效且可扩展的方法。现有的许多MF方法都严重依赖显式反馈。通常,这些数据类型可能非常稀疏。因此,这些方法可能效果不佳。为了解决这些挑战,我们通过结合隐式反馈作为补充信息,提出了基于概率MF的潜在因子模型。具体而言,显式和隐式反馈矩阵同时分解为共享子空间。然后,使用梯度下降算法共同优化潜在因子向量。使用MovieLens数据集的实验结果表明,所提出的算法优于基线。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号