通过图神经网络在Spotify实现个性化有声读物推荐

Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks

March 8, 2024

作者: 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

cs.AI

摘要

在不断发展的数字音频领域中，以其音乐和谈话内容而闻名的Spotify最近向其庞大用户群引入了有声读物。尽管前景看好，但这一举措给个性化推荐带来了重大挑战。与音乐和播客不同，最初需要付费获取的有声读物在购买前无法轻松浏览，这使得推荐的相关性面临更高的风险。此外，将新的内容类型引入现有平台会面临极端的数据稀疏性，因为大多数用户对这种新内容类型并不熟悉。最后，向数百万用户推荐内容要求模型反应迅速且具有可扩展性。为了解决这些挑战，我们利用播客和音乐用户偏好，引入了2T-HGNN，这是一个包含异质图神经网络（HGNNs）和双塔（2T）模型的可扩展推荐系统。这种新颖方法揭示了项目之间微妙的关系，同时确保了低延迟和复杂性。我们将用户从HGNN图中分离出来，并提出了一种创新的多链接邻居采样器。这些选择，连同双塔组件，显著降低了HGNN模型的复杂性。涉及数百万用户的实证评估显示，在个性化推荐质量方面取得了显著改善，导致新有声读物的启动率增加了46％，流媒体率提升了23％。有趣的是，我们的模型影响不仅限于有声读物，还使得像播客这样的成熟产品受益。

English

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.