Deep Learning Based Recommender System

By Shuai Zhang, Lina Yao, Aixin Sun, Yi Tay. 2017

1,327 citations recorded by the source corpus.

With the growing volume of online information, recommender systems have been an effective strategy to overcome information overload. The utility of recommender systems cannot be overstated, given their widespread adoption in many web applications, along with their potential impact to ameliorate many problems related to over-choice. In recent years, deep learning has garnered considerable interest in many research fields such as computer vision and natural language processing, owing not only to stellar performance but also to the attractive property of learning feature representations from scratch. The influence of deep learning is also pervasive, recently demonstrating its effectiveness when applied to information retrieval and recommender systems research. The field of deep learning in recommender system is flourishing. This article aims to provide a comprehensive review of recent research efforts on deep learning-based recommender systems. More concretely, we provide and devise a taxonomy of deep learning-based recommendation models, along with a comprehensive summary of the state of the art. Finally, we expand on current trends and provide new perspectives pertaining to this new and exciting development of the field.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

How researchers see this paper

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

In Artificial Intelligence

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Yongfeng Zhang
5. Xu Chen
6. Meng Wang
7. Wayne Xin Zhao
8. Fuli Feng

In Computer Vision and Pattern Recognition

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Meng Wang
5. Yongfeng Zhang
6. Fuli Feng
7. Xu Chen
8. Richang Hong

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Meng Wang
5. Yongfeng Zhang
6. Xu Chen
7. Fuli Feng
8. Wayne Xin Zhao

Citations in the corpus

• Explainable Recommendation: A Survey and New Perspectives (2018, methodology): “For example, Zhang et al. (2014a) defined the explainable recommendation problem, and proposed an Explicit Factor”
• Financial Aspect and Sentiment Predictions with Deep Neural Networks: An Ensemble Approach (2018, methodology): “1 INTRODUCTION Deep learning [10] techniques such as Convolutional Neural Networks (CNNs) [11] for processing data in the form ofmultiple arrays, or Recurrent Neural Networks (RNNs) such as Long Short-Term Memory neural networks (LSTMs) [5] for tasks with sequential inputs, have been widely adopted ”
• A review on deep learning for recommender systems: challenges and remedies (2018, background): “Recently, Zhang et al. (2017a) have published a comprehensive survey on deep learningbased recommender systems.”
• Reinforcement Learning based Recommender Systems: A Survey (2021, background): “[14] provide a comprehensive survey on deep learning based RSs.”
• Deep Item-based Collaborative Filtering for Top-N Recommendation (2018, background): “ure the nonlinear relations. 5.3 Deep Collaborative Filtering Models More recent evidence has suggested that integrating deep learning with recommender systems can significantly boost the performance [4, 45]. Salakhutdinov et al.[31] firstly proposed to exploit two-layer Restricted Boltzmann Machine”
• CoupleNet: Paying Attention to Couples with Coupled Attention for Relationship Recommendation (2018, methodology): “(Zhang, Yao, and Sun 2017) provides a comprehensive overview of deep learning methods for CF. Notably, our approach also follows the neural IR approach which is mainly concerned with modeling document-query pairs (Severyn and Moschitti 2015; Tay et al. 2017; Tay, Tuan, and Hui 2017) or user-item…”
• Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond (2021, methodology): “For many web applications, the recommendation systems are an essential method for providing a better user experience [193].”
• Potential, challenges and future directions for deep learning in prognostics and health management applications (2020, background): “Hence, they are well-suited to the application of DL technologies (Zhang et al., 2019c).”
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms (2020, background): “The huge business valuemakes recommender systems become a longstanding research topic, with a large number of new models proposed each year [83].”
• Advances and Challenges in Conversational Recommender Systems: A Survey (2021, background): “are survey papers focusing on certain cutting-edge aspects in recommender systems, such as the bias issues and debiasing methods [24], explainability/interpretability [244], evaluation issues [177], and novel methods that leverage deep neural networks [242, 220, 221], knowledge graphs [61], or reinf”
• Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning (2018, background): “The other topic closely related to this category is deep learning based recommender system, which is able to effectively capture the non-linear and non-trivial user-item relationships, and enables the codification of more complex abstractions as data representations in the higher layers [32].”
• Distilling Structured Knowledge into Embeddings for Explainable and Accurate Recommendation (2019, neutral): “[41] for a more comprehensive review.”
• Recommendation system based on deep learning methods: a systematic review and new directions (2019, background): “Recently Zhang et al. (2018) presented a review on the deep learning based RS models.”
• All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda (2021, background): “ing [220], [221], computer vision [222], [223], and recommender systems [224], [225].”
• Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks (2019, methodology): “and these interactions change over time [4, 5, 17, 21, 34, 37, 48].”