Deep Unified Representation for Heterogeneous Recommendation

TL;DR

This paper introduces a deep unified representation model for heterogeneous recommendation systems that effectively models diverse item types, leveraging their attributes to improve recommendation accuracy and address data sparsity issues.

Contribution

It proposes a novel kernel-based neural network that jointly models heterogeneous items while maintaining their feature space topology, with theoretical proof of its representation ability.

Findings

Achieves 4.1% to 34.9% AUC lift over existing models

Improves online CTR by 3.7%

Demonstrates effectiveness on real-world datasets

Abstract

Recommendation system has been a widely studied task both in academia and industry. Previous works mainly focus on homogeneous recommendation and little progress has been made for heterogeneous recommender systems. However, heterogeneous recommendations, e.g., recommending different types of items including products, videos, celebrity shopping notes, among many others, are dominant nowadays. State-of-the-art methods are incapable of leveraging attributes from different types of items and thus suffer from data sparsity problems. And it is indeed quite challenging to represent items with different feature spaces jointly. To tackle this problem, we propose a kernel-based neural network, namely deep unified representation (or DURation) for heterogeneous recommendation, to jointly model unified representations of heterogeneous items while preserving their original feature space topology structures. Theoretically, we prove the representation ability of the proposed model. Besides, we conduct extensive experiments on real-world datasets. Experimental results demonstrate that with the unified representation, our model achieves remarkable improvement (e.g., 4.1% ~ 34.9% lift by AUC score and 3.7% lift by online CTR) over existing state-of-the-art models.