Shapley Value-driven Data Pruning for Recommender Systems

Abstract

Recommender systems often suffer from noisy interactions like accidental clicks or popularity bias. Existing denoising methods typically identify users' intent in their interactions, and filter out noisy interactions that deviate from the assumed intent. However, they ignore that interactions deemed noisy could still aid model training, while some ``clean'' interactions offer little learning value. To bridge this gap, we propose Shapley Value-driven Valuation (SVV), a framework that evaluates interactions based on their objective impact on model training rather than subjective intent assumptions. In SVV, a real-time Shapley value estimation method is devised to quantify each interaction's value based on its contribution to reducing training loss. Afterward, SVV highlights the interactions with high values while downplaying low ones to achieve effective data pruning for recommender systems. In addition, we develop a simulated noise protocol to examine the performance of various denoising approaches systematically. Experiments on four real-world datasets show that SVV outperforms existing denoising methods in both accuracy and robustness. Further analysis also demonstrates that our SVV can preserve training-critical interactions and offer interpretable noise assessment. This work shifts denoising from heuristic filtering to principled, model-driven interaction valuation.

In SIGKDD (2025), 10 pages

References in corpus (8)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Denoising Self-attentive Sequential Recommendation
• Self-Guided Learning to Denoise for Robust Recommendation
• AutoDenoise: Automatic Data Instance Denoising for Recommendations
• Uncovering User Interest from Biased and Noised Watch Time in Video Recommendation
• Denoising User-aware Memory Network for Recommendation
• Interpretable Triplet Importance for Personalized Ranking
• Beyond Models! Explainable Data Valuation and Metric Adaption for Recommendation