Deep Collaborative Filtering via Marginalized Denoising Auto-encoder

@article{Li2015DeepCF,
  title={Deep Collaborative Filtering via Marginalized Denoising Auto-encoder},
  author={Sheng Li and Jaya Kawale and Yun Raymond Fu},
  journal={Proceedings of the 24th ACM International on Conference on Information and Knowledge Management},
  year={2015}
}
  • Sheng Li, Jaya Kawale, Y. Fu
  • Published 17 October 2015
  • Computer Science
  • Proceedings of the 24th ACM International on Conference on Information and Knowledge Management
Collaborative filtering (CF) has been widely employed within recommender systems to solve many real-world problems. [] Key Method Deep learning models have emerged as very appealing in learning effective representations in many applications. In particular, we propose a general deep architecture for CF by integrating matrix factorization with deep feature learning.

Figures and Tables from this paper

Robust Representations for Collaborative Filtering
TLDR
A general deep architecture for CF is proposed by integrating matrix factorization with deep feature learning, which leads to a parsimonious fit over the latent features as indicated by its improved performance in comparison to prior state-of-art models over four large datasets for the tasks of movie/book recommendation and response prediction.
Deep Transfer Collaborative Filtering with Geometric Structure Preservation for Cross-Domain Recommendation
TLDR
A general architecture of deep transfer collaborative filtering with geometry preservation (DTCFGP) is proposed by integrating cross-domain collective matrix factorization, deep feature learning and the graph modeling, which demonstrates the effectiveness of the proposed approach in comparison to state-of-the-art approaches.
Deep Transfer Collaborative Filtering for Recommender Systems
TLDR
A generic deep transfer collaborative filtering (DTCF) architecture, which integrates collective matrix factorization and deep transfer learning, is proposed, which employs non-negative matrix tri-factorization and stacked denoising autoencoder (SDAE) in both source and target domains.
A Hybrid Collaborative Filtering Model with Deep Structure for Recommender Systems
TLDR
This work utilizes advances of learning effective representations in deep learning, and proposes a hybrid model which jointly performs deep users and items’ latent factors learning from side information and collaborative filtering from the rating matrix.
Neural Variational Hybrid Collaborative Filtering
TLDR
A Neural Variational Hybrid Collaborative Filtering, NVHCF, which considers both the generative processes of users and items, and the prior of latent factors of Users and items to be side informationspecific, which enables the model to alleviate matrix sparsity and learn better latent representations ofUsers and items.
Neural Variational Collaborative Filtering for Top-K Recommendation
TLDR
A novel deep hybrid framework for top-K recommendation, named Neural Variational Collaborative Filtering (NVCF), where user and item side information is incorporated into the generative processes of user and items, to alleviate data sparsity and learn better latent representations of users and items.
Attentive and Collaborative Deep Learning for Recommendation
TLDR
This paper proposes a deep collaborative filtering model with attention mechanism that can significantly outperform the state-of-the-artdeep collaborative filtering models and user preferences learned are interpretable.
Neural Variational Matrix Factorization with Side Information for Collaborative Filtering
TLDR
The NVMF consists of two end-to-end variational autoencoder neural networks, namely user neural network and item neural network respectively, which are capable of learning complex nonlinear distributed representations of users and items through the proposed variational inference.
Neural variational collaborative filtering with side information for top-K recommendation
TLDR
A novel deep hybrid framework for top-k recommendation, neural variational collaborative filtering (NVCF), and three NVCF-based instantiation is designed, which significantly outperform the state-of-the-art hybrid CF models and VAE-based methods.
...
...

References

SHOWING 1-10 OF 46 REFERENCES
Collaborative Deep Learning for Recommender Systems
TLDR
A hierarchical Bayesian model called collaborative deep learning (CDL), which jointly performs deep representation learning for the content information and collaborative filtering for the ratings (feedback) matrix is proposed, which can significantly advance the state of the art.
SCMF: Sparse Covariance Matrix Factorization for Collaborative Filtering
TLDR
This work investigates the covariance matrix of the latent features learned from real data to address the important issue of what structure should be imposed on the features, and proposes an MF model with a sparse covariance prior which favors a sparse yet non-diagonal covariance Matrix.
Scalable Variational Bayesian Matrix Factorization with Side Information
TLDR
This paper presents a scalable inference for VBMF with side information, the complexity of which is linear in the rank K of factor matrices, which can be easily parallelized on multi-core systems.
Bayesian Matrix Factorization with Side Information and Dirichlet Process Mixtures
TLDR
A Bayesian matrix factorization model that performs regression against side information known about the data in addition to the observations is introduced and applied to the Netflix Prize problem of predicting movie ratings given an incomplete user-movie ratings matrix.
Personalized recommendation via cross-domain triadic factorization
TLDR
This paper proposes a generalized Cross Domain Triadic Factorization (CDTF) model over the triadic relation user-item-domain, which can better capture the interactions between domain-specific user factors and item factors.
Coupled Item-Based Matrix Factorization
TLDR
This paper proposes an attribute-based coupled similarity measure to capture the implicit relationships between items, and integrates the implicit item coupling into MF to form the Coupled Item-based Matrix Factorization (CIMF) model.
Deep content-based music recommendation
TLDR
This paper proposes to use a latent factor model for recommendation, and predict the latent factors from music audio when they cannot be obtained from usage data, and shows that recent advances in deep learning translate very well to the music recommendation setting, with deep convolutional neural networks significantly outperforming the traditional approach.
Distributed Stochastic ADMM for Matrix Factorization
TLDR
Experiments show that the proposed distributed stochastic alternating direction methods of multipliers (DS-ADMM) model can outperform other state-of-the-art distributed MF models in terms of both efficiency and accuracy.
Incorporating Side Information in Probabilistic Matrix Factorization with Gaussian Processes
TLDR
This work proposes a framework for incorporating side information in Probabilistic matrix factorization by coupling together multi- ple PMF problems via Gaussian process priors, and replaces scalar latent features with func- tions that vary over the covariate space.
Factorization meets the neighborhood: a multifaceted collaborative filtering model
TLDR
The factor and neighborhood models can now be smoothly merged, thereby building a more accurate combined model and a new evaluation metric is suggested, which highlights the differences among methods, based on their performance at a top-K recommendation task.
...
...