TFPS: A Temporal Filtration-enhanced Positive Sample Set Construction Method for Implicit Collaborative Filtering

2026-02-25

AI Summary

This work addresses the limitations of existing implicit collaborative filtering methods, which overly rely on negative sampling while neglecting positive sample quality and failing to effectively model the temporal dynamics of user preferences. To this end, we propose a novel time-aware positive sample construction mechanism that, for the first time, incorporates temporal interval information into the positive sample denoising process. Specifically, we construct a weighted user–item bipartite graph using a time-decay function and apply hierarchical filtering combined with layer-wise enhancement to generate high-quality positive samples. The proposed approach is highly generalizable and can be seamlessly integrated into various implicit CF models and negative sampling strategies. Extensive experiments on three real-world datasets demonstrate significant improvements in Recall@k and NDCG@k, confirming the method’s effectiveness and strong generalization capability.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Recommender Systems
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Content-based information diffusion
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

The negative sampling strategy can effectively train collaborative filtering (CF) recommendation models based on implicit feedback by constructing positive and negative samples. However, existing methods primarily optimize the negative sampling process while neglecting the exploration of positive samples. Some denoising recommendation methods can be applied to denoise positive samples within negative sampling strategies, but they ignore temporal information. Existing work integrates sequential information during model aggregation but neglects time interval information, hindering accurate capture of users' current preferences. To address this problem, from a data perspective, we propose a novel temporal filtration-enhanced approach to construct a high-quality positive sample set. First, we design a time decay model based on interaction time intervals, transforming the original graph into a weighted user-item bipartite graph. Then, based on predefined filtering operations, the weighted user-item bipartite graph is layered. Finally, we design a layer-enhancement strategy to construct a high-quality positive sample set for the layered subgraphs. We provide theoretical insights into why TFPS can improve Recall@k and NDCG@k, and extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed method. Additionally, TFPS can be integrated with various implicit CF recommenders or negative sampling methods to enhance its performance.

Problem

• implicit collaborative filtering
• positive sample construction
• temporal information
• time interval
• user preference

Innovation

• temporal filtration
• positive sample construction
• time decay model
• implicit collaborative filtering
• weighted bipartite graph