Hybrid Interest Modeling for Long-tailed Users

TL;DR

This paper introduces the Hybrid Interest Modeling (HIM) network, which effectively captures both personalized and semi-personalized user interests to improve recommendations for long-tailed users with sparse data.

Contribution

The paper proposes the HIM network with UBP and UBC modules, addressing data sparsity and privacy issues in long-tailed user interest modeling.

Findings

HIM outperforms state-of-the-art baselines on public datasets.

The UBP module captures fine-grained personalized interests.

The UBC module learns latent interest groups with self-supervised learning.

Abstract

User behavior modeling is a key technique for recommender systems. However, most methods focus on head users with large-scale interactions and hence suffer from data sparsity issues. Several solutions integrate side information such as demographic features and product reviews, another is to transfer knowledge from other rich data sources. We argue that current methods are limited by the strict privacy policy and have low scalability in real-world applications and few works consider the behavioral characteristics behind long-tailed users. In this work, we propose the Hybrid Interest Modeling (HIM) network to hybrid both personalized interest and semi-personalized interest in learning long-tailed users' preferences in the recommendation. To achieve this, we first design the User Behavior Pyramid (UBP) module to capture the fine-grained personalized interest of high confidence from sparse even noisy positive feedbacks. Moreover, the individual interaction is too sparse and not enough for modeling user interest adequately, we design the User Behavior Clustering (UBC) module to learn latent user interest groups with self-supervised learning mechanism novelly, which capture coarse-grained semi-personalized interest from group-item interaction data. Extensive experiments on both public and industrial datasets verify the superiority of HIM compared with the state-of-the-art baselines.