Collaborative Variational Autoencoder for Recommender Systems

By Xiaopeng Li, James She. Knowledge Discovery and Data Mining, 2017

458 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Signal Processing

View Paper: https://www.semanticscholar.org/paper/fb641dbada6a27b009cb28a629e7f02fbeec6e10

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Liqiang Nie
5. Fuli Feng
6. Meng Wang
7. Yi Tay
8. Le Wu

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Meng Wang
5. Yi Tay
6. Liqiang Nie
7. Naomie Binti Salim
8. Aminu Da’u

In Signal Processing

1. Dit-Yan Yeung
2. Hao Wang
3. Aminu Da’u
4. Peng Cui
5. Liqiang Nie
6. Tat-seng Chua
7. Chuan Shi
8. Chang Zhou

Citations in the corpus

• Multi-Pointer Co-Attention Networks for Recommendation (2018, background): “A separate class of deep models based on auto-encoders [14, 23, 31] have also been proposed for recommendation tasks.”
• Are we really making much progress? A worrying analysis of recent neural recommendation approaches (2019, methodology): “The baselines in [23] include three recent deep learning models and as well as Collaborative Topic Regression (CTR).”
• When large language models meet personalization: perspectives of challenges and opportunities (2023, unknown): “CVAE [89] introduces a collaborative variational autoencoder that learns probabilistic textual features.”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, background): “proposed to simultaneously recover the ratingmatrix and the side content information with a variational autoencoder [74].”
• Learning Disentangled Representations for Recommendation (2019, methodology): “Preventing mode collapse We use cosine similarity, instead of the inner product similarity adopted by most existing deep learning methods [32, 31, 18].”
• A Survey on Bayesian Deep Learning (2016, background): “What is more, one can also derive Bayesian treatments for concrete models, leading to more robust predictions [68, 121].”
• Deep Learning Based Recommender System (2017, background): “Another extension of CDL is the Collaborative Variational Autoencoder (CVAE) [89], which replaces the deep neural component of CDL with a variational autoencoder.”
• Latent Relational Metric Learning via Memory-based Attention for Collaborative Ranking (2017, background): “ recommender networks [34] which focuses on sequence aware recommendations and Deep Co-operative Networks (DeepCoNN) [39] that exploits review information for recommendation. Autoencoder based models [14, 38] have also been proposed for CF. In the more closely related domain of collaborative •lterin”
• A review on deep learning for recommender systems: challenges and remedies (2018, methodology): “…Kyo-Joong et al. (2014) Yang et al. (2017) Du et al. (2017) Tang et al. (2015) Lian et al. (2017) Barbieri et al. (2017) Suglia et al. (2017) Li and She (2017) Cao et al. (2017) Oramas et al. (2017) Kumar et al. (2017) Suzuki and Ozaki (2017) Obadić et al. (2017) Soh et al. (2017) Xu et…”
• Towards Bayesian Deep Learning: A Survey (2016, methodology): “ [66] LV ✓ Symmetric CDL [66] LV ✓ Collaborative Deep Ranking [131] HV ✓ Collaborative Knowledge Base Embedding [132] HV ✓ Collaborative Recurrent AE [122] HV ✓ Collaborative Variational Autoencoders [68] HV ✓ Topic Models Relational SDAE HV ✓ Deep Poisson Factor Analysis with Sigmoid Belief Network”
• Diffusion Recommender Model (2023, background): “Besides, generative models are specialized to capture the complex and non-linear relations between user preference and interactions as detailed in [19, 20, 36].”
• Neural Graph Collaborative Filtering (2019, background): “Specifically, there are many other forms of structural information can be useful for understanding user behaviors, such as the cross features in contentrich [14, 37] and context-aware [25, 28] recommendation, and item knowledge graph [1, 39, 44], and social networks [38].”
• MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation (2019, background): “Recently, to improve performance, the recommendations have been made using deep learning methods [10, 24, 28]; however, the cold-start problem remains for new users who rate only a few items.”
• Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation (2020, background): “, age and gender of users) are often exploited [17, 35].”
• Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback (2020, background): “Comparing with the work focusing on explicit feedback [5, 17, 22], profiling the user from implicit feedback is more practical and challenge.”
• Recommendation system based on deep learning methods: a systematic review and new directions (2019, methodology): “A similar method was introduced in Li and She (2017) to better learn probabilistic latent variables for content information and easily incorporate side information from multimedia source for RS. Li et (2015) designed a general deep learning method called deep CF which combines matrix factorization…”