Abstract
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.