Knowledge-Enhanced Top-K Recommendation in Poincaré Ball
Preprint
Abstract
Personalized recommender systems are increasingly important as more content and services become available and users struggle to identify what might interest them. Thanks to the ability for providing rich information, knowledge graphs (KGs) are being incorporated to enhance the recommendation performance and interpretability. To effectively make use of the knowledge graph, we propose a recommendation model in the hyperbolic space, which facilitates the learning of the hierarchical structure of knowledge graphs. Furthermore, a hyperbolic attention network is employed to determine the relative importances of neighboring entities of a certain item. In addition, we propose an adaptive and fine-grained regularization mechanism to adaptively regularize items and their neighboring representations. Via a comparison using three real-world datasets with state-of-the-art methods, we show that the proposed model outperforms the best existing models by 2-16% in terms of NDCG@K on Top-K recommendation.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Multi-graph Convolution Collaborative Filtering2019
- Hierarchical Gating Networks for Sequential Recommendation2019
- Gated Attentive-Autoencoder for Content-Aware Recommendation2019
- Regularizing Matrix Factorization with User and Item Embeddings for Recommendation2018
- Neural Factorization Machines for Sparse Predictive Analytics2017
- A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and ApplicationsIEEE Transactions on Evolutionary Computation, 2017
- Collaborative Knowledge Base Embedding for Recommender Systems2016
- Collaborative Denoising Auto-Encoders for Top-N Recommender Systems2016
- Learning recommender systems with adaptive regularization2012
- Collaborative Filtering for Implicit Feedback Datasets2008