Deep content-based music recommendation

By Aäron van den Oord, Sander Dieleman, Benjamin Schrauwen. 2013

1,265 citations recorded by the source corpus.

Subfields: Natural Language Processing, Recommender Systems

How researchers see this paper

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

In Natural Language Processing

1. Jianfeng Gao
2. Li Deng
3. Xiaodong He
4. Kyunghyun Cho
5. Dong Yu
6. Quoc V. Le
7. Yoshua Bengio
8. Mohit Bansal

In Recommender Systems

1. Xiangnan He
2. Xing Xie
3. Yongfeng Zhang
4. Xiang Wang
5. Tat-seng Chua
6. Xu Chen
7. Dit-Yan Yeung
8. Hao Wang

Citations in the corpus

• On Sampling Strategies for Neural Network-based Collaborative Filtering (2017, methodology): “It is worth noting that several existing stateof-the-art models [1, 4, 30] are special cases of our framework (e.”
• SoundNet: Learning Sound Representations from Unlabeled Video (2016, methodology): “Sound Recognition: Although large-scale audio understanding has been extensively studied in the context of music [5, 37] and speech recognition [10], we focus on understanding natural, in-the-wild sounds.”
• Collaborative Deep Learning for Recommender Systems (2014, background): “On music recommendation, [21, 39] directly use conventional CNN or deep belief networks (DBN) to assist representation learning for content information, but the deep learning components of their models are deterministic without modeling the noise and hence they are less robust.”
• Variational Autoencoders for Collaborative Filtering (2018, background): “Besides being applied in session-based sequential recommendation (see Section 2.1), various approaches [2, 28, 47, 48] have applied neural networks to incorporate side information into collaborative filtering models to better handle the cold-start problem.”
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems (2018, background): “We also do not consider non-deep learning approaches for generating item/content embeddings, since other works have already proven state-of-the-art performance of deep learning approaches for generating such embeddings [9, 12, 24].”
• Neural Collaborative Filtering (2017, neutral): “ACM 978-1-4503-4913-0/17/04. http://dx.doi.org/10.1145/3038912.3052569 .”
• Deep Neural Networks for YouTube Recommendations (2016, background): “Recommending YouTube videos is extremely challenging from three major perspectives: • Scale: Many existing recommendation algorithms proven to work well on small problems fail to operate on our scale.”
• Session-based Recommendations with Recurrent Neural Networks (2015, neutral): “In Van den Oord et al. (2013) a convolutional deep network is used to extract feature from music files that are then used in a factor model.”
• Deep Learning: Methods and Applications (2014, methodology): “[371] on content-based music recommendation using deep learning methods.”
• Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time (2017, background): “Many state-of-the-art web-scale recommendation systems are content-based, often using deep neural networks [6, 8, 11, 29].”
• Ask the GRU: Multi-task Learning for Deep Text Recommendations (2016, neutral): “Van den Oord et al. [41], Wang and Wang [42] developed music recommender systems which use features extracted from the music audio using convolutional neural networks (CNN) or deep belief networks.”
• DeepFM: A Factorization-Machine based Neural Network for CTR Prediction (2017, methodology): “Several deep learning models are proposed in recommendation tasks other than CTR prediction (e.g., [ Covington et al. , 2016; Salakhutdi-nov et al. , 2007; van den Oord et al. , 2013; Wu et al. , 2016; Zheng et al. , 2016; Wu et al. , 2017; Zheng et al. , 2017 ] ).”
• Neural Input Search for Large Scale Recommendation Models (2019, background): “For large scale recommendation problems, great results have also been reported by leveraging advanced representation learning components, such as CNN ([12], [21]), RNN ([1], [8]), etc.”
• A Hybrid Collaborative Filtering Model with Deep Structure for Recommender Systems (2017, background): “Moreover, work (Van den Oord, Diele- man, and Schrauwen 2013; Wang and Wang 2014) directly uses convolutional neural network(CNN) or deep belief network(DBN) to obtain latent factors for content information, but they are content-based methods which only infer latent factors for items and the…”
• Collaborative Variational Autoencoder for Recommender Systems (2017, methodology): “4 and 5 show the results that compare CTR, DeepMusic, CDL and CVAE using the two datasets under both the sparse (P = 1) and dense (P = 10) se ings.”
• Deep Collaborative Filtering via Marginalized Denoising Auto-encoder (2015, methodology): “Categories and Subject Descriptors H.2.8 [Database Management]: Data Mining; H.3.3 [Information Search Retrieval]: Information Filtering Keywords Collaborative filtering; matrix factorization; deep learning; denoising auto-encoder”
• Graph Neural Networks for Social Recommendation (2019, methodology): “Some recent efforts have applied deep neural networks to recommendation tasks and shown promising results [41], but most of them used deep neural networks to model audio features of music [32], textual description of items [3, 33], and visual content of images [40].”
• Log2Intent: Towards Interpretable User Modeling via Recurrent Semantics Memory Unit (2019, background): “Lots of research efforts have been made for this task by considering user data such as rating [5], contents [2, 17, 32], and reviews [39].”
• Audio Visual Attribute Discovery for Fine-Grained Object Recognition (2018, background): “With the development of deep neural network, the sound related applications has been extensively studies e.g., music recognition (Van den Oord, Dieleman, and Schrauwen 2013) and speech recognition (Hannun et al. 2014).”