Learning Robust Recommenders through Cross-Model Agreement

Abstract

Learning from implicit feedback is one of the most common cases in the application of recommender systems. Generally speaking, interacted examples are considered as positive while negative examples are sampled from uninteracted ones. However, noisy examples are prevalent in real-world implicit feedback. A noisy positive example could be interacted but it actually leads to negative user preference. A noisy negative example which is uninteracted because of unawareness of the user could also denote potential positive user preference. Conventional training methods overlook these noisy examples, leading to sub-optimal recommendations. In this work, we propose a novel framework to learn robust recommenders from implicit feedback. Through an empirical study, we find that different models make relatively similar predictions on clean examples which denote the real user preference, while the predictions on noisy examples vary much more across different models. Motivated by this observation, we propose denoising with cross-model agreement(DeCA) which aims to minimize the KL-divergence between the real user preference distributions parameterized by two recommendation models while maximizing the likelihood of data observation. We employ the proposed DeCA on four state-of-the-art recommendation models and conduct experiments on four datasets. Experimental results demonstrate that DeCA significantly improves recommendation performance compared with normal training and other denoising methods. Codes will be open-sourced.

arXiv comment12 pages, 23 figures

References in corpus (9)

• Neural Graph Collaborative Filtering
• KGAT: Knowledge Graph Attention Network for Recommendation
• Tutorial on Variational Autoencoders
• IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
• Denoising Implicit Feedback for Recommendation
• RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback
• Reinforced Negative Sampling over Knowledge Graph for Recommendation
• Learning with Bad Training Data via Iterative Trimmed Loss Minimization
• To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions

Cited by in corpus (9)

• Robust Preference-Guided Denoising for Graph based Social Recommendation
• Self-Guided Learning to Denoise for Robust Recommendation
• AutoDenoise: Automatic Data Instance Denoising for Recommendations
• Knowledge-refined Denoising Network for Robust Recommendation
• Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
• Uncovering User Interest from Biased and Noised Watch Time in Video Recommendation
• Unleashing the Power of Large Language Model for Denoising Recommendation
• Shapley Value-driven Data Pruning for Recommender Systems
• Enhancing Recommendation with Denoising Auxiliary Task