Shapley Value-driven Data Pruning for Recommender Systems

TL;DR

This paper introduces SVV, a Shapley value-based framework for data pruning in recommender systems that evaluates interactions by their actual contribution to training, improving robustness and accuracy.

Contribution

The paper presents a novel, model-driven approach to data denoising using real-time Shapley value estimation, moving beyond heuristic filtering methods.

Findings

SVV outperforms existing denoising methods in accuracy.

SVV enhances robustness against noisy interactions.

The method preserves training-critical interactions.

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.