Deep Unified Representation for Heterogeneous Recommendation

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.

12 pages, 4 figures, accepted by the ACM Web Conference 2022 (WWW '22)

References in corpus (6)

• Domain Generalization via Invariant Feature Representation
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Universality, Characteristic Kernels and RKHS Embedding of Measures
• Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation
• DDTCDR: Deep Dual Transfer Cross Domain Recommendation
• Selective Transfer Learning for Cross Domain Recommendation