Hyperbolic Neural Collaborative Recommender
This work addresses recommendation systems for users by improving accuracy through hyperbolic representations, but it is incremental as it builds on existing deep learning and geometry techniques.
The paper tackled collaborative filtering by proposing Hyperbolic Neural Collaborative Recommender (HNCR), which uses hyperbolic geometry and deep learning to model user-item relations, and it outperformed Euclidean methods and state-of-the-art baselines in experiments.
This paper explores the use of hyperbolic geometry and deep learning techniques for recommendation. We present Hyperbolic Neural Collaborative Recommender (HNCR), a deep hyperbolic representation learning method that exploits mutual semantic relations among users/items for collaborative filtering (CF) tasks. HNCR contains two major phases: neighbor construction and recommendation framework. The first phase introduces a neighbor construction strategy to construct a semantic neighbor set for each user and item according to the user-item historical interaction. In the second phase, we develop a deep framework based on hyperbolic geometry to integrate constructed neighbor sets into recommendation. Via a series of extensive experiments, we show that HNCR outperforms its Euclidean counterpart and state-of-the-art baselines.