HI-Series Algorithms A Hybrid of Substance Diffusion Algorithm and Collaborative Filtering

2025-03-03

AI Summary

Recommender systems face a long-standing trade-off between accuracy and diversity: Item-based Collaborative Filtering (ItemCF) enhances diversity at the expense of accuracy, while network-based diffusion methods (e.g., Mass Diffusion, MD) prioritize accuracy but degrade diversity. To address this, we propose the HI family of nonlinear hybrid algorithms—a scalable, unified framework that adaptively integrates ItemCF with multiple diffusion models (MD, HHP, BHC, BD) via a learnable parameter ε. Unlike prior linear ensembles, HI employs nonlinear weighting to preserve complementary strengths across paradigms, enabling simultaneous optimization of recommendation quality and novelty under both sparse and dense data regimes. Evaluated on benchmark datasets (e.g., MovieLens), HI achieves consistent improvements: F1-score gains of 0.8–5.2%, up to 18.6% higher Diversity@20, and markedly enhanced robustness and novelty in sparse settings.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Recommendation systems face the challenge of balancing accuracy and diversity, as traditional collaborative filtering (CF) and network-based diffusion algorithms exhibit complementary limitations. While item-based CF (ItemCF) enhances diversity through item similarity, it compromises accuracy. Conversely, mass diffusion (MD) algorithms prioritize accuracy by favoring popular items but lack diversity. To address this trade-off, we propose the HI-series algorithms, hybrid models integrating ItemCF with diffusion-based approaches (MD, HHP, BHC, BD) through a nonlinear combination controlled by parameter $epsilon$. This hybridization leverages ItemCF's diversity and MD's accuracy, extending to advanced diffusion models (HI-HHP, HI-BHC, HI-BD) for enhanced performance. Experiments on MovieLens, Netflix, and RYM datasets demonstrate that HI-series algorithms significantly outperform their base counterparts. In sparse data ($20%$ training), HI-MD achieves a $0.8%$-$4.4%$ improvement in F1-score over MD while maintaining higher diversity (Diversity@20: 459 vs. 396 on MovieLens). For dense data ($80%$ training), HI-BD improves F1-score by $2.3%$-$5.2%$ compared to BD, with diversity gains up to $18.6%$. Notably, hybrid models consistently enhance novelty in sparse settings and exhibit robust parameter adaptability. The results validate that strategic hybridization effectively breaks the accuracy-diversity trade-off, offering a flexible framework for optimizing recommendation systems across data sparsity levels.

Problem

• Balancing accuracy and diversity in recommendation systems
• Overcoming limitations of traditional collaborative filtering and diffusion algorithms
• Enhancing performance in both sparse and dense data scenarios

Innovation

• Hybrid algorithms combining ItemCF and diffusion models
• Nonlinear combination controlled by parameter ε
• Enhanced accuracy and diversity in recommendation systems