Leveraging Artist Catalogs for Cold-Start Music Recommendation

2026-04-08

AI Summary

This work addresses the cold-start problem for newly released music tracks, which suffer from a lack of user interaction data, by framing it as a “semi-cold-start” scenario. The proposed model, ACARec, innovatively leverages the hierarchical structure of artists to generate collaborative filtering (CF) embeddings for new tracks by aggregating CF signals from the artist’s historical catalog. It integrates audio, textual, metadata, and artist-level information through an attention mechanism, thereby overcoming the limitations of conventional content-based approaches that rely solely on item features. Experimental results demonstrate that ACARec more than doubles performance over pure content-based baselines in terms of Recall and NDCG, and significantly outperforms them in tasks involving discovery of new artists and prediction of popularity for niche tracks.

Abstract

The item cold-start problem poses a fundamental challenge for music recommendation: newly added tracks lack the interaction history that collaborative filtering (CF) requires. Existing approaches often address this problem by learning mappings from content features such as audio, text, and metadata to the CF latent space. However, previous works either omit artist information or treat it as just another input modality, missing the fundamental hierarchy of artists and items. Since most new tracks come from artists with previous history available, we frame cold-start track recommendation as 'semi-cold' by leveraging the rich collaborative signal that exists at the artist level. We show that artist-aware methods can more than double Recall and NDCG compared to content-only baselines, and propose ACARec, an attention-based architecture that generates CF embeddings for new tracks by attending over the artist's existing catalog. We show that our approach has notable advantages in predicting user preferences for new tracks, especially for new artist discovery and more accurate estimation of cold item popularity.

Problem

• cold-start
• music recommendation
• artist catalog
• collaborative filtering
• item cold-start

Innovation

• cold-start recommendation
• artist-aware modeling
• attention mechanism
• collaborative filtering
• music recommendation