Towards Reliable Negative Sampling for Recommendation with Implicit Feedback via In-Community Popularity

2026-02-21

AI Summary

In recommendation systems relying solely on implicit feedback, the absence of true negative samples poses a significant challenge for negative sampling, as it is difficult to simultaneously ensure authenticity, difficulty, and interpretability. To address this issue, this work proposes an Intra-Community Popularity-based Negative Sampling (ICPNS) strategy that, for the first time, integrates user community structure with intra-community item popularity to approximate item exposure probability and identify high-quality negative samples that closely resemble genuinely unexposed yet ignored items. The proposed method seamlessly integrates into both graph neural network and matrix factorization models. Extensive experiments demonstrate that ICPNS consistently outperforms existing negative sampling approaches across four benchmark datasets, delivering stable performance gains in graph-based recommender systems and remaining highly competitive in matrix factorization frameworks.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Community question answering

Abstract

Learning from implicit feedback is a fundamental problem in modern recommender systems, where only positive interactions are observed and explicit negative signals are unavailable. In such settings, negative sampling plays a critical role in model training by constructing negative items that enable effective preference learning and ranking optimization. However, designing reliable negative sampling strategies remains challenging, as they must simultaneously ensure realness, hardness, and interpretability. To this end, we propose \textbf{ICPNS (In-Community Popularity Negative Sampling)}, a novel framework that leverages user community structure to identify reliable and informative negative samples. Our approach is grounded in the insight that item exposure is driven by latent user communities. By identifying these communities and utilizing in-community popularity, ICPNS effectively approximates the probability of item exposure. Consequently, items that are popular within a user's community but remain unclicked are identified as more reliable true negatives. Extensive experiments on four benchmark datasets demonstrate that ICPNS yields consistent improvements on graph-based recommenders and competitive performance on MF-based models, outperforming representative negative sampling strategies under a unified evaluation protocol.

Problem

• negative sampling
• implicit feedback
• recommender systems
• user communities
• true negatives

Innovation

• Negative Sampling
• Implicit Feedback
• User Community
• In-Community Popularity
• Recommendation