Portal de Periódicos da CAPES

Artist Similarity for Everyone: A Graph Neural Network Approach

2022; Ubiquity Press; Volume: 5; Issue: 1 Linguagem: Inglês

10.5334/tismir.143

2514-3298

Filip Korzeniowski, Sergio Oramas, Fabien Gouyon,

Music Technology and Sound Studies

Artist similarity plays an important role in organizing, understanding, and subsequently, facilitating discovery in large collections of music. In this paper, we present a hybrid approach to computing similarity between artists using graph neural networks trained with triplet loss. The novelty of using a graph neural network architecture is to combine the topology of a graph of artist connections with content features to embed artists into a vector space that encodes similarity. Additionally, we propose a simple and effective regularization method— connection dropout —which aims at improving results for long-tail artists, for which few existing connections are known. To evaluate the proposed method, we use two datasets: the open OLGA dataset, which contains artist similarities from AllMusic, together with content features from AcousticBrainz, and a larger, proprietary dataset. We find that using graph neural networks yields superior overall results compared to state-of-the-art methods. Beyond the overall evaluation, we investigate the effectiveness of the proposed model for long-tail artists. Such artists may benefit less from graph-based methods, since they typically have few known connections. We show that the proposed regularization approach clearly improves the performance for long-tail artists, without negatively affecting results for well-connected ones; it computes high-quality embeddings and good similarity scores for everyone.