Of Spiky SVDs and Music Recommendation
Not on the map. Why?
Abstract (arXiv)
The truncated singular value decomposition is a widely used methodology in music recommendation for direct similar-item retrieval or embedding musical items for downstream tasks. This paper investigates a curious effect that we show naturally occurring on many recommendation datasets: spiking formations in the embedding space. We first propose a metric to quantify this spiking organization's strength, then mathematically prove its origin tied to underlying communities of items of varying internal popularity. With this new-found theoretical understanding, we finally open the topic with an industrial use case of estimating how music embeddings' top-k similar items will change over time under the addition of data.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 55 references that are in the map. First posted on arXiv 30 Jun 2023.
Builds on
20 of 55 references.
References · 20
- 2019Diffusion Improves Graph Learningcited by 414
- 2019Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approachescited by 181
- 2013Consistency of spectral clustering in stochastic block modelscited by 128
- 2020Neural Collaborative Filtering vs. Matrix Factorization Revisitedcited by 123
- 2019A Troubling Analysis of Reproducibility and Progress in Recommender Systems Researchcited by 65
- 2021Towards Learning Universal Audio Representationscited by 51
- 2019On the Difficulty of Evaluating Baselines: A Study on Recommender Systemscited by 46
- 2013Regularized Spectral Clustering under the Degree-Corrected Stochastic Blockmodelcited by 45
- 2020Reliable Graph Neural Networks via Robust Aggregationcited by 43
- 2017Current Challenges and Visions in Music Recommender Systems Researchcited by 42
- 2016Community Detection in Degree-Corrected Block Modelscited by 36
- 2019Gravity-Inspired Graph Autoencoders for Directed Link Predictioncited by 28
8 more
- 2021A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Appscited by 21
- 2018Word2Vec applied to Recommendation: Hyperparameters Mattercited by 20
- 2021Towards a Better Understanding of Linear Models for Recommendationcited by 18
- 2022Explainability in Music Recommender Systemscited by 15
- 2021Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoderscited by 12
- 2018Regularized Singular Value Decomposition and Application to Recommender Systemcited by 6
- 2022Learning Unsupervised Hierarchies of Audio Conceptscited by 3
- 2020Popularity and Centrality in Spotify Networks: Critical transitions in eigenvector centralitycited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.