SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation

Abstract

Knowledge Graphs (KGs) enhance recommender systems but face challenges from inherent noise, sparsity, and Euclidean geometry's inadequacy for complex relational structures, critically impairing representation learning, especially for long-tail entities. Existing methods also often lack adaptive multi-source signal fusion tailored to item popularity. This paper introduces SPARK, a novel multi-stage framework systematically tackling these issues. SPARK first employs Tucker low-rank decomposition to denoise KGs and generate robust entity representations. Subsequently, an SVD-initialized hybrid geometric GNN concurrently learns representations in Euclidean and Hyperbolic spaces; the latter is strategically leveraged for its aptitude in modeling hierarchical structures, effectively capturing semantic features of sparse, long-tail items. A core contribution is an item popularity-aware adaptive fusion strategy that dynamically weights signals from collaborative filtering, refined KG embeddings, and diverse geometric spaces for precise modeling of both mainstream and long-tail items. Finally, contrastive learning aligns these multi-source representations. Extensive experiments demonstrate SPARK's significant superiority over state-of-the-art methods, particularly in improving long-tail item recommendation, offering a robust, principled approach to knowledge-enhanced recommendation. Implementation code is available at https://github.com/Applied-Machine-Learning-Lab/SPARK.

Accepted by CIKM' 25

References in corpus (24)

• Geometric deep learning: going beyond Euclidean data
• KGAT: Knowledge Graph Attention Network for Recommendation
• Knowledge Graphs
• Self-supervised Graph Learning for Recommendation
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
• Hyperbolic Geometry of Complex Networks
• Knowledge Graph Convolutional Networks for Recommender Systems
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
• TuckER: Tensor Factorization for Knowledge Graph Completion
• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• Knowledge Graph Contrastive Learning for Recommendation
• Deep Reinforcement Learning for Page-wise Recommendations
• Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning
• A Comprehensive Survey on Deep Graph Representation Learning
• Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System
• HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization
• HICF: Hyperbolic Informative Collaborative Filtering
• HAMUR: Hyper Adapter for Multi-Domain Recommendation
• Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems
• AutoDenoise: Automatic Data Instance Denoising for Recommendations
• Exploration and Regularization of the Latent Action Space in Recommendation
• Large Knowledge Model: Perspectives and Challenges
• The Impacts of Data, Ordering, and Intrinsic Dimensionality on Recall in Hierarchical Navigable Small Worlds