Million Song Dataset Challenge !

By Feng Niu, Cathy T. Zhang. 2012

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xiangnan He
2. Yi Tay
3. Yoshua Bengio
4. Dacheng Tao
5. Quoc V. Le
6. Trevor Darrell
7. Sergey Levine
8. Yi Yang

Citations in the corpus

• Deep content-based music recommendation (2013, methodology): “The dataset was used in the Million Song Dataset challenge [14] last year.”
• Current challenges and visions in music recommender systems research (2017, methodology): “This variation of MAP was popularized by Kaggle competitions [97] about recommender systems and has been used in several other research works, consider for example [8,124].”
• Efficient top-n recommendation for very large scale binary rated datasets (2013, methodology): “The Million Song Dataset Challenge [10] was a large scale, music recommendation challenge, where the task is to predict which songs a user will listen to, provided the listening history of a user.”
• Improving Content-based and Hybrid Music Recommendation using Deep Learning (2014, methodology): “Most existing recommenders are based on CF because of its superior accuracy [9].”
• Collaborative Metric Learning (2017, methodology): “Finally, for EchoNest data [34], we include the songs a user listened to for at least 5 times as positive feedback.”
• MLbase: A Distributed Machine-learning System (2013, background): “The Million Song Dataset Challenge [6] is to predict the listening behavior of a set of 110,000 music listeners (i.e., the test-set), deciding which songs of the Million Song Dataset [10] they will listen to based on partial listening history and the listening history of 1M other users (i.e., the tr”
• A Generic Coordinate Descent Framework for Learning from Implicit Feedback (2016, background): “BPR tackles this issue by sampling negative items, but it has been shown that BPR has convergence problems when the number of items is large [7, 12].”