2000 character limit reached
Track Mix Generation on Music Streaming Services using Transformers (2307.03045v1)
Published 6 Jul 2023 in cs.IR, cs.LG, cs.SD, and eess.AS
Abstract: This paper introduces Track Mix, a personalized playlist generation system released in 2022 on the music streaming service Deezer. Track Mix automatically generates "mix" playlists inspired by initial music tracks, allowing users to discover music similar to their favorite content. To generate these mixes, we consider a Transformer model trained on millions of track sequences from user playlists. In light of the growing popularity of Transformers in recent years, we analyze the advantages, drawbacks, and technical challenges of using such a model for mix generation on the service, compared to a more traditional collaborative filtering approach. Since its release, Track Mix has been generating playlists for millions of users daily, enhancing their music discovery experience on Deezer.
- Sudipto Banerjee and Anindya Roy. 2014. Linear Algebra and Matrix Analysis for Statistics. CRC Press.
- Carousel Personalization in Music Streaming Apps with Contextual Bandits. Proceedings of the 14th ACM Conference on Recommender Systems (2020), 420–425.
- A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval.
- Matrix Factorization Model in Collaborative Filtering Algorithms: A Survey. Procedia Computer Science 49 (2015), 136–146.
- Flow Moods: Recommending Music by Moods on Deezer. In Proceedings of the 16th ACM Conference on Recommender Systems. 452–455.
- Gianni Brauwers and Flavius Frasincar. 2023. A General Survey on Attention Mechanisms in Deep Learning. IEEE Transactions on Knowledge and Data Engineering 35, 4 (2023), 3279–3298.
- A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2021), 2601–2609.
- Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems 33 (2020), 1877–1901.
- Pre-trained Transformers: An Empirical Comparison. Machine Learning with Applications 9 (2022), 100334.
- RecSys Challenge 2018: Automatic Music Playlist Continuation. Proceedings of the 12th ACM Conference on Recommender Systems (2018), 527–528.
- Deezer. 2023. https://www.deezer.com.
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171–4186.
- ONNX Technical Documentation. 2023. Quantize ONNX Models. https://onnxruntime.ai/docs/performance/model-optimizations/quantization.html.
- ONNX: Open Neural Network Exchange. 2023. https://github.com/onnx/onnx.
- Billion-Scale Similarity Search with GPUs. IEEE Transactions on Big Data 7, 3 (2019), 535–547.
- Wang-Cheng Kang and Julian McAuley. 2018. Self-Attentive Sequential Recommendation. Proceedings of the 2018 IEEE International Conference on Data Mining (2018), 197–206.
- Transformers in Vision: A Survey. ACM Computing Surveys 54, 10s (2022), 1–41.
- Yehuda Koren and Robert Bell. 2015. Advances in Collaborative Filtering. Recommender Systems Handbook (2015), 77–118.
- Approximate Nearest Neighbor Search on High Dimensional Data – Experiments, Analyses, and Improvement. IEEE Transactions on Knowledge and Data Engineering 32, 8 (2019), 1475–1488.
- Improving Language Understanding by Generative Pre-Training. OpenAI Technical Report (2018).
- Current Challenges and Visions in Music Recommender Systems Research. Proceedings of the International Journal of Multimedia Information Retrieval 7, 2 (2018), 95–116.
- BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer. Proceedings of the 28th ACM International Conference on Information and Knowledge Management (2019), 1441–1450.
- Attention Is All You Need. Advances in Neural Information Processing Systems 30 (2017).
- An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation. ACM Transactions on Intelligent Systems and Technology 10, 5 (2019), 1–21.