HICF: Hyperbolic Informative Collaborative Filtering

Abstract

Considering the prevalence of the power-law distribution in user-item networks, hyperbolic space has attracted considerable attention and achieved impressive performance in the recommender system recently. The advantage of hyperbolic recommendation lies in that its exponentially increasing capacity is well-suited to describe the power-law distributed user-item network whereas the Euclidean equivalent is deficient. Nonetheless, it remains unclear which kinds of items can be effectively recommended by the hyperbolic model and which cannot. To address the above concerns, we take the most basic recommendation technique, collaborative filtering, as a medium, to investigate the behaviors of hyperbolic and Euclidean recommendation models. The results reveal that (1) tail items get more emphasis in hyperbolic space than that in Euclidean space, but there is still ample room for improvement; (2) head items receive modest attention in hyperbolic space, which could be considerably improved; (3) and nonetheless, the hyperbolic models show more competitive performance than Euclidean models. Driven by the above observations, we design a novel learning method, named hyperbolic informative collaborative filtering (HICF), aiming to compensate for the recommendation effectiveness of the head item while at the same time improving the performance of the tail item. The main idea is to adapt the hyperbolic margin ranking learning, making its pull and push procedure geometric-aware, and providing informative guidance for the learning of both head and tail items. Extensive experiments back up the analytic findings and also show the effectiveness of the proposed method. The work is valuable for personalized recommendations since it reveals that the hyperbolic space facilitates modeling the tail item, which often represents user-customized preferences or new products.

arXiv commentProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '22)

References in corpus (19)

• Neural Graph Collaborative Filtering
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Stochastic gradient descent on Riemannian manifolds
• Hyperbolic Graph Convolutional Neural Networks
• Representation Tradeoffs for Hyperbolic Embeddings
• Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space
• HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization
• Where are we in embedding spaces? A Comprehensive Analysis on Network Embedding Approaches for Recommender Systems
• UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation
• Hyperbolic Graph Neural Networks: A Review of Methods and Applications
• Unsupervised Text Generation by Learning from Search
• Graph-based Semi-supervised Learning: A Comprehensive Review
• SimpleX: A Simple and Strong Baseline for Collaborative Filtering
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks
• HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systems
• Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation
• Enhancing Hyperbolic Graph Embeddings via Contrastive Learning
• TeleGraph: A Benchmark Dataset for Hierarchical Link Prediction

Cited by in corpus (5)

• HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction
• HGCH: A Hyperbolic Graph Convolution Network Model for Heterogeneous Collaborative Graph Recommendation
• Hyperbolic Deep Learning for Foundation Models: A Survey
• Review-Based Hyperbolic Cross-Domain Recommendation
• SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation