Deep Matrix Factorization Models for Recommender Systems

@inproceedings{Xue2017DeepMF,
  title={Deep Matrix Factorization Models for Recommender Systems},
  author={Hong Xue and Xinyu Dai and Jianbing Zhang and Shujian Huang and Jiajun Chen},
  booktitle={IJCAI},
  year={2017}
}
Recommender systems usually make personalized recommendation with user-item interaction ratings, implicit feedback and auxiliary information. [] Key Method With this matrix as the input, we present a deep structure learning architecture to learn a common low dimensional space for the representations of users and items. Secondly, we design a new loss function based on binary cross entropy, in which we consider both explicit ratings and implicit feedback for a better optimization. The experimental results show…

Figures and Tables from this paper

BDMF: A Biased Deep Matrix Factorization Model for Recommendation
  • Changsheng MaJianjun LiPeng PanGuohui LiJ. Du
  • Computer Science
    2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI)
  • 2019
TLDR
A novel matrix factorization model with neural network architecture, named BDMF, short for Biased Deep Matrix Factorization, that introduces bias to both users and items and can be viewed as a deep neural network implementation of BiasedSVD.
Is Simple Better? Revisiting Non-Linear Matrix Factorization for Learning Incomplete Ratings
TLDR
This paper proposes a multilayer nonlinear semi-nonnegative matrix factorization method, with the motivation that user-item interactions can be modeled more accurately using a linear combination of non-linear item features.
Deep Matrix Factorization for Cross-Domain Recommendation
TLDR
This paper uses multi-layer perceptron structures to learn the representation of users and items in ML-based method and proposes Deep Matrix Factorization for Cross Domain Recommendation (DMF-CDR), which outperforms several recent popular models.
From Content Text Encoding Perspective: A Hybrid Deep Matrix Factorization Approach for Recommender System
TLDR
This work proposes an approach by using neural networks to acquire the latent factors of latent factor models, and shows that this model is effective on two benchmark datasets, outperforming some state-of-art approaches.
Neural Matrix Factorization Recommendation for User Preference Prediction Based on Explicit and Implicit Feedback
TLDR
A neural matrix factorization recommendation algorithm (EINMF) based on explicit-implicit feedback is proposed that has the feasibility, validity, and robustness fully demonstrated in comparison with multiple baseline models on two real datasets.
A Deep Latent Factor Model for High-Dimensional and Sparse Matrices in Recommender Systems
TLDR
A deep latent factor model (DLFM) is proposed for building a deep-structured RS on an HiDS matrix efficiently by sequentially connecting multiple latent factor (LF) models instead of multilayered neural networks through a nonlinear activation function.
RETHINKING GENERALIZED MATRIX FACTORIZATION
  • Computer Science
  • 2019
TLDR
The ablation study demonstrates that by using multi-hot encoding to enrich user embedding and item embedding for Generalized Matrix Factorization, better performance, faster convergence, and lower training loss can be achieved.
A Hybrid Deep Collaborative Filtering Approach for Recommender Systems
TLDR
The Weighted Parallel Deep Hybrid RS uses additional attributes of user - item matrix to alleviate the cold start problem and indicates better prediction compared to other techniques in terms of accuracy.
On the instability of embeddings for recommender systems: the case of matrix factorization
TLDR
A generalization of MF is presented, called Nearest Neighbors Matrix Factorization (NNMF), which propagates the information about items and users to their neighbors, speeding up the training procedure and extending the amount of information that supports recommendations and representations.
DCAR: Deep Collaborative Autoencoder for Recommendation with Implicit Feedback
TLDR
This work presents a novel framework, named DCAR, short for Deep Collaborative Autoencoder for Recommendation, which is designed based on the neural network architecture and empirically verifies the superior performance of DCAR on item recommendation.
...
...

References

SHOWING 1-10 OF 35 REFERENCES
Fast Matrix Factorization for Online Recommendation with Implicit Feedback
TLDR
A new learning algorithm based on the element-wise Alternating Least Squares (eALS) technique is designed, for efficiently optimizing a Matrix Factorization (MF) model with variably-weighted missing data and exploiting this efficiency to then seamlessly devise an incremental update strategy that instantly refreshes a MF model given new feedback.
VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback
TLDR
This paper proposes a scalable factorization model to incorporate visual signals into predictors of people's opinions, which is applied to a selection of large, real-world datasets and makes use of visual features extracted from product images using (pre-trained) deep networks.
TopicMF: Simultaneously Exploiting Ratings and Reviews for Recommendation
TLDR
Experimental results show the superiority of the proposed novel matrix factorization model (called TopicMF) over the state-of-the-art models, demonstrating its effectiveness for recommendation tasks.
Collaborative Filtering for Implicit Feedback Datasets
TLDR
This work identifies unique properties of implicit feedback datasets and proposes treating the data as indication of positive and negative preference associated with vastly varying confidence levels, which leads to a factor model which is especially tailored for implicit feedback recommenders.
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.
SoRec: social recommendation using probabilistic matrix factorization
TLDR
A factor analysis approach based on probabilistic matrix factorization to solve the data sparsity and poor prediction accuracy problems by employing both users' social network information and rating records is proposed.
Deep Collaborative Filtering via Marginalized Denoising Auto-encoder
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.
Neural Collaborative Filtering
TLDR
This work strives to develop techniques based on neural networks to tackle the key problem in recommendation --- collaborative filtering --- on the basis of implicit feedback, and presents a general framework named NCF, short for Neural network-based Collaborative Filtering.
Collaborative Denoising Auto-Encoders for Top-N Recommender Systems
TLDR
It is demonstrated that the proposed model is a generalization of several well-known collaborative filtering models but with more flexible components, and that CDAE consistently outperforms state-of-the-art top-N recommendation methods on a variety of common evaluation metrics.
Hidden factors and hidden topics: understanding rating dimensions with review text
TLDR
This paper aims to combine latent rating dimensions (such as those of latent-factor recommender systems) with latent review topics ( such as those learned by topic models like LDA), which more accurately predicts product ratings by harnessing the information present in review text.
...
...