📄 中文摘要
该研究提出了一种基于用户-物品-标签三元图的个性化推荐方法，利用集成扩散技术来提高推荐系统的效果。通过构建三元图模型，研究者能够更好地捕捉用户偏好和物品特征之间的复杂关系。集成扩散方法通过整合多种信息源，增强了推荐的准确性和多样性。实验结果表明，该方法在多个数据集上均优于传统的推荐算法，展示了其在实际应用中的潜力。此研究为个性化推荐领域提供了新的思路和方法，推动了相关技术的发展。
基于用户-物品-标签三元图的个性化推荐通过集成扩散
📄 English Summary
Personalized Recommendation via Integrated Diffusion on User-Item-Tag TripartiteGraphs
This research proposes a personalized recommendation method based on user-item-tag tripartite graphs, utilizing integrated diffusion techniques to enhance the effectiveness of recommendation systems. By constructing a tripartite graph model, the study captures the complex relationships between user preferences and item characteristics more effectively. The integrated diffusion approach consolidates multiple information sources, improving the accuracy and diversity of recommendations. Experimental results demonstrate that this method outperforms traditional recommendation algorithms across various datasets, showcasing its potential for real-world applications. This study offers new insights and methodologies for the field of personalized recommendations, advancing the development of related technologies.