Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks

• URL: http://arxiv.org/abs/2403.05185v1
• Date: Fri, 8 Mar 2024 09:53:07 GMT
• Title: Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks
• Authors: Marco De Nadai, Francesco Fabbri, Paul Gigioli, Alice Wang, Ang Li, Fabrizio Silvestri, Laura Kim, Shawn Lin, Vladan Radosavljevic, Sandeep Ghael, David Nyhan, Hugues Bouchard, Mounia Lalmas-Roelleke, Andreas Damianou
• Abstract summary: Spotify has recently introduced audiobooks to its vast user base. This move presents significant challenges for personalized recommendations. We propose 2T-HGNN, a scalable recommendation system comprising Heterogeneous Graph Neural Networks (HGNNs) and a Two Tower (2T) model.
• Score: 11.051929104747316
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• DFGNN: Dual-frequency Graph Neural Network for Sign-aware Feedback [51.72177873832969]
  We propose a novel model that models positive and negative feedback from a frequency filter perspective. We conduct extensive experiments on real-world datasets and demonstrate the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2024-05-24T07:07:41Z)
• MusicRL: Aligning Music Generation to Human Preferences [62.44903326718772]
  MusicRL is the first music generation system finetuned from human feedback. We deploy MusicLM to users and collect a substantial dataset comprising 300,000 pairwise preferences. We train MusicRL-U, the first text-to-music model that incorporates human feedback at scale.
  arXiv  Detail & Related papers  (2024-02-06T18:36:52Z)
• Fairness Through Domain Awareness: Mitigating Popularity Bias For Music Discovery [56.77435520571752]
  We explore the intrinsic relationship between music discovery and popularity bias. We propose a domain-aware, individual fairness-based approach which addresses popularity bias in graph neural network (GNNs) based recommender systems. Our approach uses individual fairness to reflect a ground truth listening experience, i.e., if two songs sound similar, this similarity should be reflected in their representations.
  arXiv  Detail & Related papers  (2023-08-28T14:12:25Z)
• Dual Intent Enhanced Graph Neural Network for Session-based New Item Recommendation [74.81561396321712]
  We propose a dual-intent enhanced graph neural network for session-based recommendations. We learn user intent from an attention mechanism and the distribution of historical data. By outputting new item probabilities, which contain recommendation scores of the corresponding items, the new items with higher scores are recommended to users.
  arXiv  Detail & Related papers  (2023-05-10T02:42:12Z)
• Episodes Discovery Recommendation with Multi-Source Augmentations [3.0054316799543837]
  We build upon the classical Two-Tower model and introduce the novel Multi-Source Augmentations (MSACL) to enhance episode embedding learning. Experiments on a real-world podcast recommendation dataset from a large audio streaming platform demonstrate the effectiveness of the proposed framework.
  arXiv  Detail & Related papers  (2023-01-04T18:10:26Z)
• Price DOES Matter! Modeling Price and Interest Preferences in Session-based Recommendation [55.0391061198924]
  Session-based recommendation aims to predict items that an anonymous user would like to purchase based on her short behavior sequence. It is nontrivial to incorporate price preferences for session-based recommendation. We propose a novel method Co-guided Heterogeneous Hypergraph Network (CoHHN) for session-based recommendation.
  arXiv  Detail & Related papers  (2022-05-09T10:47:15Z)
• Dual Side Deep Context-aware Modulation for Social Recommendation [50.59008227281762]
  We propose a novel graph neural network to model the social relation and collaborative relation. On top of high-order relations, a dual side deep context-aware modulation is introduced to capture the friends' information and item attraction.
  arXiv  Detail & Related papers  (2021-03-16T11:08:30Z)
• PodSumm -- Podcast Audio Summarization [0.0]
  We propose a method to automatically construct a podcast summary via guidance from the text-domain. Motivated by a lack of datasets for this task, we curate an internal dataset, find an effective scheme for data augmentation, and design a protocol to gather summaries from annotators. Our method achieves ROUGE-F(1/2/L) scores of 0.63/0.53/0.63 on our dataset.
  arXiv  Detail & Related papers  (2020-09-22T04:49:33Z)
• Recommending Podcasts for Cold-Start Users Based on Music Listening and Taste [5.429958676933934]
  We consider podcasting as an emerging medium with rapid growth in adoption. Using music consumption behavior, we examine two main techniques in inferring Spotify users preferences over more than 200k podcasts. Our results show significant improvements in consumption of up to 50% for both offline and online experiments.
  arXiv  Detail & Related papers  (2020-07-27T02:55:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.