Neural Collaborative Filtering

@article{He2017NeuralCF,
  title={Neural Collaborative Filtering},
  author={Xiangnan He and Lizi Liao and Hanwang Zhang and Liqiang Nie and Xia Hu and Tat-Seng Chua},
  journal={Proceedings of the 26th International Conference on World Wide Web},
  year={2017}
}
In recent years, deep neural networks have yielded immense success on speech recognition, computer vision and natural language processing. [] Key MethodBy replacing the inner product with a neural architecture that can learn an arbitrary function from data, we present a general framework named NCF, short for Neural network-based Collaborative Filtering. NCF is generic and can express and generalize matrix factorization under its framework.

Figures and Tables from this paper

Recommended System: Attentive 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 method named ANCF(Attention Neural network Collaborative Filtering).
Collaborative Filtering: Graph Neural Network with Attention
TLDR
This work proposes a general method called “Graph Neural Network with Attention” (GNNA), which captures CF signals based on neural networks and uses high-order connectivity to obtain neglected interactive information, thereby improving the embedding of users and items and proved the rationality and effectiveness of GNNA.
Collaborative Autoencoder for Recommender Systems
TLDR
A generic recommender framework called Neural Collaborative Autoencoder (NCAE) is presented to perform collaborative filtering, which works well for both explicit feedback and implicit feedback and can effectively capture the relationship between interactions via a non-linear matrix factorization process.
Deep Collaborative Filtering Based on Outer Product
TLDR
This work proposes the Convolutional Neural Networks based Deep Collaborative Filtering model (CNN-DCF) and develops a correlation extraction module that can learn high-order correlations between item latent features and user latent features.
A Hybrid Neural Network for Collaborative Filtering
TLDR
A hybrid neural network that combines heterogeneous neural networks with different structures is proposed that is superior to the state-ofthe-art methods in terms of the item ranking.
Neural Collaborative Autoencoder
TLDR
A generic recommender framework called Neural Collaborative Autoencoder (NCAE) is presented to perform collaborative filtering, which works well for both explicit feedback and implicit feedback and can effectively capture the subtle hidden relationships between interactions via a non-linear matrix factorization process.
Collaborative filtering via heterogeneous neural networks
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.
Neural Collaborative Ranking
TLDR
This paper develops a new classification strategy based on the widely used pairwise ranking assumption, and resorts to a neural network architecture to model a user's pairwise preference between items, with the belief that neural network will effectively capture the latent structure of latent factors.
Deep Collaborative Autoencoder for Recommender Systems: A Unified Framework for Explicit and Implicit Feedback
TLDR
A novel recommender framework called Deep Collaborative Autoencoder (DCAE) for both explicit feedback and implicit feedback, which can effectively capture the relationship between interactions via its non-linear expressiveness and optimize the deep architecture of DCAE.
...
...

References

SHOWING 1-10 OF 54 REFERENCES
Collaborative Filtering with Stacked Denoising AutoEncoders and Sparse Inputs
TLDR
This paper introduces a neural network architecture which computes a non-linear matrix factorization from sparse rating inputs and provides an implementation of the algorithm as a reusable plugin for Torch, a popular neural network framework.
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.
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.
Collaborative Knowledge Base Embedding for Recommender Systems
TLDR
A heterogeneous network embedding method is adopted, termed as TransR, to extract items' structural representations by considering the heterogeneity of both nodes and relationships and a final integrated framework, which is termed as Collaborative Knowledge Base Embedding (CKE), to jointly learn the latent representations in collaborative filtering.
Learning Image and User Features for Recommendation in Social Networks
TLDR
A novel deep model is proposed which learns the unified feature representations for both users and images by transforming the heterogeneous user-image networks into homogeneous low-dimensional representations, which facilitate a recommender to trivially recommend images to users by feature similarity.
A Neural Autoregressive Approach to Collaborative Filtering
TLDR
Experimental results show that CF-NADE with a single hidden layer beats all previous state-of-the-art methods on MovieLens 1M, MovieLens 10M, and Netflix datasets, and adding more hidden layers can further improve the performance.
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.
Probabilistic Matrix Factorization
TLDR
The Probabilistic Matrix Factorization (PMF) model is presented, which scales linearly with the number of observations and performs well on the large, sparse, and very imbalanced Netflix dataset and is extended to include an adaptive prior on the model parameters.
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.
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.
...
...