MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation

Abstract

The long-tailed problem is a long-standing challenge in Sequential Recommender Systems (SRS) in which the problem exists in terms of both users and items. While many existing studies address the long-tailed problem in SRS, they only focus on either the user or item perspective. However, we discover that the long-tailed user and item problems exist at the same time, and considering only either one of them leads to sub-optimal performance of the other one. In this paper, we propose a novel framework for SRS, called Mutual Enhancement of Long-Tailed user and item (MELT), that jointly alleviates the long-tailed problem in the perspectives of both users and items. MELT consists of bilateral branches each of which is responsible for long-tailed users and items, respectively, and the branches are trained to mutually enhance each other, which is trained effectively by a curriculum learning-based training. MELT is model-agnostic in that it can be seamlessly integrated with existing SRS models. Extensive experiments on eight datasets demonstrate the benefit of alleviating the long-tailed problems in terms of both users and items even without sacrificing the performance of head users and items, which has not been achieved by existing methods. To the best of our knowledge, MELT is the first work that jointly alleviates the long-tailed user and item problems in SRS.

9 pages; Accepted by SIGIR 2023

References in corpus (8)

• Filter-enhanced MLP is All You Need for Sequential Recommendation
• Lightweight Self-Attentive Sequential Recommendation
• Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation
• ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance
• LTE4G: Long-Tail Experts for Graph Neural Networks
• Learning Transferrable Parameters for Long-tailed Sequential User Behavior Modeling
• Beyond Learning from Next Item: Sequential Recommendation via Personalized Interest Sustainability
• Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-training

Cited by in corpus (2)

• MUSE: Music Recommender System with Shuffle Play Recommendation Enhancement
• Generative Archetype-Grounded Item Representations for Sequential Recommendation