Side Information Fusion for Recommender Systems over Heterogeneous Information Network

TL;DR

This paper introduces a novel framework for enhancing collaborative filtering in recommender systems by effectively fusing heterogeneous side information through metagraphs, matrix factorization, and attention mechanisms, leading to improved recommendation accuracy.

Contribution

It proposes a new HIN-based recommendation framework that captures complex semantic similarities and fuses multiple information sources using MF, FM, and hierarchical attention, outperforming existing methods.

Findings

Significant improvement over state-of-the-art methods in four real-world datasets.

Effective modeling of complex semantic similarities via metagraphs.

Successful fusion of heterogeneous information sources enhances recommendation quality.

Abstract

Collaborative filtering (CF) has been one of the most important and popular recommendation methods, which aims at predicting users' preferences (ratings) based on their past behaviors. Recently, various types of side information beyond the explicit ratings users give to items, such as social connections among users and metadata of items, have been introduced into CF and shown to be useful for improving recommendation performance. However, previous works process different types of information separately, thus failing to capture the correlations that might exist across them. To address this problem, in this work, we study the application of heterogeneous information network (HIN) to enhance CF-based recommendation methods. However, we face challenging issues in HIN-based recommendation, i.e., how to capture similarities of complex semantics between users and items in a HIN, and how to effectively fuse these similarities to improve final recommendation performance. To address these issues, we apply metagraph to similarity computation and solve the information fusion problem with a ``matrix factorization (MF) + factorization machine (FM)'' framework. For the MF part, we obtain the user-item similarity matrix from each metagraph and then apply low-rank matrix approximation to obtain latent features for both users and items. For the FM part, we apply FM with Group lasso (FMG) on the features obtained from the MF part to train the recommending model and, at the same time, identify the useful metagraphs. Besides FMG, a two-stage method, we further propose an end-to-end method, hierarchical attention fusing (HAF), to fuse metagraph based similarities for the final recommendation. Experimental results on four large real-world datasets show that the two proposed frameworks significantly outperform existing state-of-the-art methods in terms of recommendation performance.