GLocal-K: Global and Local Kernels for Recommender Systems

27 Aug 2021  ·  Soyeon Caren Han, Taejun Lim, Siqu Long, Bernd Burgstaller, Josiah Poon ·

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.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Recommendation Systems Douban Monti GLocal-K RMSE 0.7208 # 1
Recommendation Systems MovieLens 100K GLocal-K RMSE (u1 Splits) 0.8889 # 2
Recommendation Systems MovieLens 1M GLocal-K RMSE 0.8227 # 1

Methods


No methods listed for this paper. Add relevant methods here