arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.12184cs.IRcs.AI
收藏

GLocal-K:推荐系统的全局和局部核

GLocal-K: Global and Local Kernels for Recommender Systems

The University of Sydney(悉尼大学);Yonsei University(延世大学)

Soyeon Caren Han, Taejun Lim, Siqu Long, Bernd Burgstaller, Josiah Poon

摘要:

推荐系统通常在高维稀疏用户项矩阵上操作。矩阵补全是一项非常具有挑战性的任务,它基于数百万其他用户每个人都看到了数千个项目的一个小子集来预测一个人的兴趣。我们提出了一个全球本地内核为基础的矩阵完成框架,名为GLocal-K,其目的是概括和表示一个高维稀疏的用户项矩阵进入低维空间的少量重要功能。我们的GLocal-K可以分为两个主要阶段。首先,我们用局部核化权重矩阵预训练自动编码器,它通过使用2d-RBF核将数据从一个空间转换到特征空间。然后,预先训练的自动编码器使用评级矩阵进行微调,评级矩阵由基于卷积的全局内核产生,该内核捕获每个项目的特征。我们应用我们的GLocal-K模型下的极端低资源设置,其中只包括一个用户项目的评级矩阵,没有边信息。我们的模型在ML-100 K、ML-1 M和豆瓣三个协同过滤基准上的性能优于最先进的基线。

英文摘要:

Recommender systems typically operate on high-dimensional sparse user-item matrices. Matrix completion is a very challenging task to predict one's interest based on millions of other users having each seen a small subset of thousands of items. We propose a Global-Local Kernel-based matrix completion framework, named GLocal-K, that aims to generalise and represent a high-dimensional sparse user-item matrix entry into a low dimensional space with a small number of important features. Our GLocal-K can be divided into two major stages. First, we pre-train an auto encoder with the local kernelised weight matrix, which transforms the data from one space into the feature space by using a 2d-RBF kernel. Then, the pre-trained auto encoder is fine-tuned with the rating matrix, produced by a convolution-based global kernel, which captures the characteristics of each item. We apply our GLocal-K model under the extreme low-resource setting, which includes only a user-item rating matrix, with no side information. Our model outperforms the state-of-the-art baselines on three collaborative filtering benchmarks: ML-100K, ML-1M, and Douban.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑