New method uses time to denoise collaborative filtering models

Researchers have developed a novel method called TintCF that leverages temporal information to denoise collaborative filtering models. This approach addresses the challenge of noisy interactions in implicit feedback data, which can degrade recommendation system performance. TintCF generates time-aware user and item embeddings to identify and rectify these noisy edges, with two proposed strategies: reweighting the adjacency matrix or the loss function. Experiments on real-world datasets demonstrate the effectiveness of using time information to improve model robustness. AI

IMPACT This research could improve the accuracy and robustness of recommendation systems by mitigating the impact of noisy user-item interaction data.

RANK_REASON Academic paper detailing a new method for denoising collaborative filtering models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• information retrieval
• Litmaps
• ScienceCast
• scite Smart Citations
• TintCF
• Xinyu He

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →