Aspect-Level Deep Collaborative Filtering via Heterogeneous Information Networks

@inproceedings{Han2018AspectLevelDC,
  title={Aspect-Level Deep Collaborative Filtering via Heterogeneous Information Networks},
  author={Xiaotian Han and Chuan Shi and Senzhang Wang and Philip S. Yu and L. Song},
  booktitle={IJCAI},
  year={2018}
}
Latent factor models have been widely used for recommendation. Most existing latent factor models mainly utilize the rating information between users and items, although some recently extended models add some auxiliary information to learn a unified latent factor between users and items. The unified latent factor only represents the latent features of users and items from the aspect of purchase history. However, the latent features of users and items may stem from different aspects, e.g., the… 

Figures and Tables from this paper

Combining Meta-Graph and Attention for Recommendation over Heterogenous Information Network
TLDR
An approach for the recommendation over HIN, called MGAR, which combines Meta-Graph and Attention to address the challenge, and experiments over two real datasets indicate MGAR achieves state-of-the-art performance.
Neural Graph Filtering for Context-aware Recommendation
TLDR
This paper proposes a neural graph filtering method for context-aware recommendation, called NGF, which is a case-by-case algorithm for personalized recommendation on HINs, which predicts the further behavior by all its similar historical behaviors.
Graph Filtering for Recommendation on Heterogeneous Information Networks
TLDR
An adaptive framework is proposed to learn the weights of different semantic edges and products an optimized predicted rating and demonstrates that GF is effective to handler the sparsity issue of recommendation and outperforms the state-of-the-art techniques.
Unified Embedding Model over Heterogeneous Information Network for Personalized Recommendation
TLDR
A HIN based unified embedding model for recommendation, called HueRec, which combines these two parts into an end-to-end model to avoid useful information lost in initial phases and can measure users’ preferences on meta-paths to improve the performances of personalized recommendation.
Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems
TLDR
This paper extends Stacked Denoising Autoencoders to effectively fuse review texts and item contents with the rating matrix in both auxiliary and target domains and utilizes a multi-layer perceptron to transfer user latent factors between the two domains to address the data sparsity and cold start issues.
Heterogeneous Graph Embedding for Cross-Domain Recommendation Through Adversarial Learning
TLDR
A novel cross-domain recommender framework called ECHCDR (Embedding content and heterogeneous network for cross- domain recommendation), which contains two major steps of content embedding and heterogeneity network embedding that can effectively alleviate the data sparsity issue.
Recent Advances in Heterogeneous Relation Learning for Recommendation
TLDR
This survey reviews the development of recommendation frameworks with the focus on heterogeneous relational learning, which consists of different types of dependencies among users and items, and discusses the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information.
DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation
TLDR
This paper uses meta relations to decompose high-order connectivity between node pairs and proposes a disentangled embedding propagation layer which can iteratively identify the major aspect of meta relations in a heterogeneous information network.
Sequence-aware Heterogeneous Graph Neural Collaborative Filtering
TLDR
This paper proposes a novel Sequence-aware Heterogeneous graph neural Collaborative Filtering model, called SHCF, which can address the above problems by considering both the high-order heterogeneous collaborative signals and sequential information.
GAMMA: A Graph and Multi-view Memory Attention Mechanism for Top-N Heterogeneous Recommendation
TLDR
An end-to-end neural network model – GAMMA (Graph and Multi-view Memory Attention mechanism) is proposed that aims to replace the offline meta-path based similarity or commuting matrix computation with a graph attention mechanism.
...
...

References

SHOWING 1-10 OF 40 REFERENCES
Integrating heterogeneous information via flexible regularization framework for recommendation
TLDR
It is found that attribute information of users and items can significantly improve recommendation accuracy, and their contribution seems more important than that of social relations.
Heterogeneous Information Network Embedding for Recommendation
TLDR
A novel heterogeneous network embedding based approach for HIN based recommendation, called HERec is proposed, which shows the capability of the HERec model for the cold-start problem, and reveals that the transformed embedding information from HINs can improve the recommendation performance.
Deep Matrix Factorization Models for Recommender Systems
TLDR
A novel matrix factorization model with neural network architecture is proposed that outperformed other state-of-the-art methods on several benchmark datasets and considers both explicit ratings and implicit feedback for a better optimization.
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.
Personalized entity recommendation: a heterogeneous information network approach
TLDR
This paper proposes to combine heterogeneous relationship information for each user differently and aim to provide high-quality personalized recommendation results using user implicit feedback data and personalized recommendation models.
Semantic Path based Personalized Recommendation on Weighted Heterogeneous Information Networks
TLDR
This paper is the first to propose the weighted HIN and weighted meta path concepts to subtly depict the path semantics through distinguishing different link attribute values, and proposes a semantic path based personalized recommendation method SemRec to predict the rating scores of users on items.
Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks
TLDR
This paper introduces the concept of meta-graph to HIN-based recommendation, and solves the information fusion problem with a "matrix factorization + factorization machine (FM)" approach, and proposes to use FM with Group lasso (FMG) to automatically learn from the observed ratings to effectively select useful meta- graph based features.
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.
Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering
TLDR
This paper builds novel models for the One-Class Collaborative Filtering setting, where the goal is to estimate users' fashion-aware personalized ranking functions based on their past feedback and combines high-level visual features extracted from a deep convolutional neural network, users' past feedback, as well as evolving trends within the community.
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.
...
...