Self-Guided Learning to Denoise for Robust Recommendation

Abstract

The ubiquity of implicit feedback makes them the default choice to build modern recommender systems. Generally speaking, observed interactions are considered as positive samples, while unobserved interactions are considered as negative ones. However, implicit feedback is inherently noisy because of the ubiquitous presence of noisy-positive and noisy-negative interactions. Recently, some studies have noticed the importance of denoising implicit feedback for recommendations, and enhanced the robustness of recommendation models to some extent. Nonetheless, they typically fail to (1) capture the hard yet clean interactions for learning comprehensive user preference, and (2) provide a universal denoising solution that can be applied to various kinds of recommendation models. In this paper, we thoroughly investigate the memorization effect of recommendation models, and propose a new denoising paradigm, i.e., Self-Guided Denoising Learning (SGDL), which is able to collect memorized interactions at the early stage of the training (i.e., "noise-resistant" period), and leverage those data as denoising signals to guide the following training (i.e., "noise-sensitive" period) of the model in a meta-learning manner. Besides, our method can automatically switch its learning phase at the memorization point from memorization to self-guided learning, and select clean and informative memorized data via a novel adaptive denoising scheduler to improve the robustness. We incorporate SGDL with four representative recommendation models (i.e., NeuMF, CDAE, NGCF and LightGCN) and different loss functions (i.e., binary cross-entropy and BPR loss). The experimental results on three benchmark datasets demonstrate the effectiveness of SGDL over the state-of-the-art denoising methods like T-CE, IR, DeCA, and even state-of-the-art robust graph-based methods like SGCN and SGL.

arXiv commentAccepted by SIGIR2022

References in corpus (10)

• Neural Graph Collaborative Filtering
• Self-supervised Graph Learning for Recommendation
• Classification with Noisy Labels by Importance Reweighting
• Denoising Implicit Feedback for Recommendation
• AutoDebias: Learning to Debias for Recommendation
• Adversarial Sampling and Training for Semi-Supervised Information Retrieval
• Learning Robust Recommenders through Cross-Model Agreement
• To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions
• Robust Learning by Self-Transition for Handling Noisy Labels
• Sampler Design for Bayesian Personalized Ranking by Leveraging View Data

Cited by in corpus (11)

• Robust Preference-Guided Denoising for Graph based Social Recommendation
• Knowledge-refined Denoising Network for Robust Recommendation
• Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction
• Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
• Uncovering User Interest from Biased and Noised Watch Time in Video Recommendation
• Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising
• Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis
• Unleashing the Power of Large Language Model for Denoising Recommendation
• CombiGCN: An effective GCN model for Recommender System
• Shapley Value-driven Data Pruning for Recommender Systems
• Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing