Leveraging Negative Signals with Self-Attention for Sequential Music Recommendation

TL;DR

This paper introduces a transformer-based model for sequential music recommendation that incorporates negative feedback through contrastive learning, leading to improved recommendation accuracy.

Contribution

It proposes a novel contrastive learning approach to integrate negative session-level feedback into self-attentive recommendation models for music.

Findings

Consistent performance improvements over baseline models.

Effective use of negative feedback in training enhances recommendation quality.

Demonstrates the applicability of contrastive loss in music recommendation tasks.

Abstract

Music streaming services heavily rely on their recommendation engines to continuously provide content to their consumers. Sequential recommendation consequently has seen considerable attention in current literature, where state of the art approaches focus on self-attentive models leveraging contextual information such as long and short-term user history and item features; however, most of these studies focus on long-form content domains (retail, movie, etc.) rather than short-form, such as music. Additionally, many do not explore incorporating negative session-level feedback during training. In this study, we investigate the use of transformer-based self-attentive architectures to learn implicit session-level information for sequential music recommendation. We additionally propose a contrastive learning task to incorporate negative feedback (e.g skipped tracks) to promote positive hits and penalize negative hits. This task is formulated as a simple loss term that can be incorporated into a variety of deep learning architectures for sequential recommendation. Our experiments show that this results in consistent performance gains over the baseline architectures ignoring negative user feedback.