AutoDenoise: Automatic Data Instance Denoising for Recommendations

Abstract

Historical user-item interaction datasets are essential in training modern recommender systems for predicting user preferences. However, the arbitrary user behaviors in most recommendation scenarios lead to a large volume of noisy data instances being recorded, which cannot fully represent their true interests. While a large number of denoising studies are emerging in the recommender system community, all of them suffer from highly dynamic data distributions. In this paper, we propose a Deep Reinforcement Learning (DRL) based framework, AutoDenoise, with an Instance Denoising Policy Network, for denoising data instances with an instance selection manner in deep recommender systems. To be specific, AutoDenoise serves as an agent in DRL to adaptively select noise-free and predictive data instances, which can then be utilized directly in training representative recommendation models. In addition, we design an alternate two-phase optimization strategy to train and validate the AutoDenoise properly. In the searching phase, we aim to train the policy network with the capacity of instance denoising; in the validation phase, we find out and evaluate the denoised subset of data instances selected by the trained policy network, so as to validate its denoising ability. We conduct extensive experiments to validate the effectiveness of AutoDenoise combined with multiple representative recommender system models.

arXiv comment9 pages, 4 figures, 5 tables, conference

References in corpus (6)

• Deep Reinforcement Learning for Page-wise Recommendations
• Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning
• Denoising Implicit Feedback for Recommendation
• Deep Reinforcement Learning for List-wise Recommendations
• Learning Robust Recommenders through Cross-Model Agreement
• What is Next when Sequential Prediction Meets Implicitly Hard Interaction?

Cited by in corpus (9)

• Dataset Regeneration for Sequential Recommendation
• Efficient and Robust Regularized Federated Recommendation
• Shapley Value-driven Data Pruning for Recommender Systems
• Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
• SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
• Empowering Denoising Sequential Recommendation with Large Language Model Embeddings
• Enhancing Recommendation with Denoising Auxiliary Task
• Prompt Tuning as User Inherent Profile Inference Machine
• ORCA: Mitigating Over-Reliance for Multi-Task Dwell Time Prediction with Causal Decoupling