# Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks

arXiv: https://arxiv.org/abs/2403.05185 · HTML: https://mlsanity.com/paper/2403.05185/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 8 Mar 2024.

## Builds on (most cited first, 22 of 22)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [A Survey on Knowledge Graph-Based Recommender Systems](https://mlsanity.com/paper/2003.00911/) (2020)
- [Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation](https://mlsanity.com/paper/2110.08727/) (2021)
- [GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems](https://mlsanity.com/paper/2008.13517/) (2020)
- [Linkless Link Prediction via Relational Distillation](https://mlsanity.com/paper/2210.05801/) (2022)
- [Learned Low Precision Graph Neural Networks](https://mlsanity.com/paper/2009.09232/) (2020)
- [Link Prediction with Non-Contrastive Learning](https://mlsanity.com/paper/2211.14394/) (2022)
- [Deep Feature Learning for Graphs](https://mlsanity.com/paper/1704.08829/) (2017)
- [MultiBiSage: A Web-Scale Recommendation System Using Multiple Bipartite Graphs at Pinterest](https://mlsanity.com/paper/2205.10666/) (2022)
- [Episodes Discovery Recommendation with Multi-Source Augmentations](https://mlsanity.com/paper/2301.01737/) (2023)
- [UBER-GNN: A User-Based Embeddings Recommendation based on Graph Neural Networks](https://mlsanity.com/paper/2008.02546/) (2020)

## Built on by (most cited first, 14 of 14)

- [Towards Graph Foundation Models for Personalization](https://mlsanity.com/paper/2403.07478/) (2024)
- [Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models](https://mlsanity.com/paper/2505.17051/) (2025)
- [An Automatic Graph Construction Framework based on Large Language Models for Recommendation](https://mlsanity.com/paper/2412.18241/) (2024)
- [Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation](https://mlsanity.com/paper/2507.15826/) (2025)
- [Graph Neural Networks on Quantum Computers](https://mlsanity.com/paper/2405.17060/) (2024)
- [A Fair Evaluation of Graph Foundation Models for Node Property Prediction](https://mlsanity.com/paper/2606.24509/) (2026)
- [Research on Low-Latency Inference and Training Efficiency Optimization for Graph Neural Network and Large Language Model-Based Recommendation Systems](https://mlsanity.com/paper/2507.01035/) (2025)
- [Mamba for Scalable and Efficient Personalized Recommendations](https://mlsanity.com/paper/2409.17165/) (2024)
- [Inductive Graph Representation Learning with Quantum Graph Neural Networks](https://mlsanity.com/paper/2503.24111/) (2025)
- [T-TExTS (Teaching Text Expansion for Teacher Scaffolding): Enhancing Text Selection in High School Literature through Knowledge Graph-Based Recommendation](https://mlsanity.com/paper/2506.12075/) (2025)
- [Real-time and personalized product recommendations for large e-commerce platforms](https://mlsanity.com/paper/2506.21368/) (2025)
- [Designing an Interpretable Interface for Contextual Bandits](https://mlsanity.com/paper/2409.15143/) (2024)
- [Creator-Side Recommender System: Challenges, Designs, and Applications](https://mlsanity.com/paper/2502.20497/) (2025)
- [Rhapsody: A Dataset for Highlight Detection in Podcasts](https://mlsanity.com/paper/2505.19429/) (2025)

## Abstract (arXiv)

In the ever-evolving digital audio landscape, Spotify, well-known for its music and talk content, has recently introduced audiobooks to its vast user base. While promising, this move presents significant challenges for personalized recommendations. Unlike music and podcasts, audiobooks, initially available for a fee, cannot be easily skimmed before purchase, posing higher stakes for the relevance of recommendations. Furthermore, introducing a new content type into an existing platform confronts extreme data sparsity, as most users are unfamiliar with this new content type. Lastly, recommending content to millions of users requires the model to react fast and be scalable. To address these challenges, we leverage podcast and music user preferences and introduce 2T-HGNN, a scalable recommendation system comprising Heterogeneous Graph Neural Networks (HGNNs) and a Two Tower (2T) model. This novel approach uncovers nuanced item relationships while ensuring low latency and complexity. We decouple users from the HGNN graph and propose an innovative multi-link neighbor sampler. These choices, together with the 2T component, significantly reduce the complexity of the HGNN model. Empirical evaluations involving millions of users show significant improvement in the quality of personalized recommendations, resulting in a +46% increase in new audiobooks start rate and a +23% boost in streaming rates. Intriguingly, our model's impact extends beyond audiobooks, benefiting established products like podcasts.