Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders

Abstract

On an artist's profile page, music streaming services frequently recommend a ranked list of "similar artists" that fans also liked. However, implementing such a feature is challenging for new artists, for which usage data on the service (e.g. streams or likes) is not yet available. In this paper, we model this cold start similar artists ranking problem as a link prediction task in a directed and attributed graph, connecting artists to their top-k most similar neighbors and incorporating side musical information. Then, we leverage a graph autoencoder architecture to learn node embedding representations from this graph, and to automatically rank the top-k most similar neighbors of new artists using a gravity-inspired mechanism. We empirically show the flexibility and the effectiveness of our framework, by addressing a real-world cold start similar artists ranking problem on a global music streaming service. Along with this paper, we also publicly release our source code as well as the industrial graph data from our experiments.

arXiv comment15th ACM Conference on Recommender Systems (RecSys 2021)

References in corpus (14)

• Auto-Encoding Variational Bayes
• A Comprehensive Survey on Graph Neural Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Link Prediction in Complex Networks: A Survey
• Graph Convolutional Matrix Completion
• Variational Graph Auto-Encoders
• The Measure and Mismeasure of Fairness
• Constrained Graph Variational Autoencoders for Molecule Design
• Current Challenges and Visions in Music Recommender Systems Research
• A Theoretical Analysis of NDCG Type Ranking Measures
• Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks
• STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
• Music Mood Detection Based On Audio And Lyrics With Deep Neural Net
• Graph Learning based Recommender Systems: A Review

Cited by in corpus (4)

• A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services
• Graph-based Recommendation for Sparse and Heterogeneous User Interactions
• To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoders
• Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation