RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems

  title={RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems},
  author={Hongwei Wang and Fuzheng Zhang and Jialin Wang and Miao Zhao and Wenjie Li and Xing Xie and Minyi Guo},
  journal={Proceedings of the 27th ACM International Conference on Information and Knowledge Management},
  • Hongwei WangFuzheng Zhang M. Guo
  • Published 9 March 2018
  • Computer Science
  • Proceedings of the 27th ACM International Conference on Information and Knowledge Management
To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph as the source of side information. To address the limitations of existing embedding-based and path-based methods for knowledge-graph-aware recommendation, we propose RippleNet, an end-to-end framework that naturally incorporates the knowledge graph… 

Figures and Tables from this paper

Exploring High-Order User Preference on the Knowledge Graph for Recommender Systems

It is found that RippleNet provides a new perspective of explainability for the recommended results in terms of the KG, and both versions of RippleNet achieve substantial gains in a variety of scenarios, including movie, book, and news recommendations, over several state of theart baselines.

A Hierarchical Knowledge and Interest Propagation Network for Recommender Systems

A Hierarchical Knowledge and Interest Propagation Network for recommendation, where a new heterogeneous propagation method is presented and it is demonstrated that the approach outperforms compelling recommender baselines.

Recommendation Algorithm Based on Knowledge Graph to Propagate User Preference

This paper proposes a model ST_RippleNet, which combines knowledge graph with deep learning, and adopts a triple-based multi-layer attention mechanism to stimulate the propagation of users' preferences on the set of knowledge entities.

Improving recommender system via knowledge graph based exploring user preference

An end-to-end framework to improve the recommender system via a knowledge graph based on fusing entity relation(KGFER), which can sufficiently capture the users’ preferences and outperforms state-of-the-art baselines.

Graph-Aware Collaborative Filtering for Top-N Recommendation

Experimental results on three real datasets indicate that the proposed Graph-aware Collaborative Filtering (GCF) is superior to the existing models in terms of accuracy and can also effectively solve the data sparsity problem of the recommender system.

Scientific and Technological News Recommendation Based on Knowledge Graph with User Perception

The knowledge graph with user perception is used to acquire the source of side information to address the limitations of existing embedding-based and path-based knowledge graph-aware recommendation methods, an end-to-end framework that integrates knowledge graph and user awareness into scientific and technological news recommendation systems.

Conditional Graph Attention Networks for Distilling and Refining Knowledge Graphs in Recommendation

This work proposes Knowledge-aware Conditional Attention Networks (KCAN), which is an end-to-end model to incorporate knowledge graph into a recommender system and can gain both representability and personalization to achieve overall performance.

Personalized Relationships-Based Knowledge Graph for Recommender Systems with Dual-View Items

The PRKG-DI symmetry model is presented, a Personalized Relationships-based Knowledge Graph for recommender systems with Dual-view Items that explores user-item relatedness by mining associated entities in the KG from user- oriented entity view and item-oriented entity view to augment item semantic information.

Social-RippleNet: Jointly modeling of ripple net and social information for recommendation

A model which jointly combines knowledge graphs and social information for recommendations to alleviate data sparsity and cold-start issues in recommender systems is proposed and comparison results show that introducing user-own features, social features, and item knowledge graph features into the model can improve the prediction effect.

Interactive Knowledge Graph Attention Network for Recommender Systems

This work proposes the Interactive Knowledge Graph Attention Network (IKGAT), which directly models user-item interaction and high-order structure information within KG and consistently outperforms the state-of-the-art approaches, especially when the dataset is sparse.



Collaborative Knowledge Base Embedding for Recommender Systems

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.

Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks

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.

Personalized entity recommendation: a heterogeneous information network approach

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.

A matrix factorization technique with trust propagation for recommendation in social networks

A model-based approach for recommendation in social networks, employing matrix factorization techniques and incorporating the mechanism of trust propagation into the model demonstrates that modeling trust propagation leads to a substantial increase in recommendation accuracy, in particular for cold start users.

Joint Topic-Semantic-aware Social Recommendation for Online Voting

This paper proposes a novel Topic-Enhanced Word Embedding (TEWE) method to learn word and document representation by jointly considering their topics and semantics, and proposes the Joint Topic-Semantic-aware social Matrix Factorization (JTS-MF) model for voting recommendation.

Sequential Recommendation with User Memory Networks

A memory-augmented neural network (MANN) integrated with the insights of collaborative filtering for recommendation is designed, which store and update users» historical records explicitly, which enhances the expressiveness of the model.

Factorization meets the neighborhood: a multifaceted collaborative filtering model

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.

SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction

This paper establishes a labeled heterogeneous sentiment dataset which consists of users» sentiment relation, social relation and profile knowledge by entity-level sentiment extraction method, and proposes a novel and flexible end-to-end Signed Heterogeneous Information Network Embedding (SHINE) framework to extract users» latent representations from heterogeneous networks and predict the sign of unobserved sentiment links.

Interpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction

The proposed convolutional neural networks with dual attention model outperforms HFT and ConvMF+ in terms of mean square errors (MSE) and the superior quality of user/item embeddings learned from the model is compared.

Knowledge Graph Embedding via Dynamic Mapping Matrix

A more fine-grained model named TransD, which is an improvement of TransR/CTransR, which not only considers the diversity of relations, but also entities, which makes it can be applied on large scale graphs.