Knowledge-refined Denoising Network for Robust Recommendation

Abstract

Knowledge graph (KG), which contains rich side information, becomes an essential part to boost the recommendation performance and improve its explainability. However, existing knowledge-aware recommendation methods directly perform information propagation on KG and user-item bipartite graph, ignoring the impacts of \textit{task-irrelevant knowledge propagation} and \textit{vulnerability to interaction noise}, which limits their performance. To solve these issues, we propose a robust knowledge-aware recommendation framework, called \textit{Knowledge-refined Denoising Network} (KRDN), to prune the task-irrelevant knowledge associations and noisy implicit feedback simultaneously. KRDN consists of an adaptive knowledge refining strategy and a contrastive denoising mechanism, which are able to automatically distill high-quality KG triplets for aggregation and prune noisy implicit feedback respectively. Besides, we also design the self-adapted loss function and the gradient estimator for model optimization. The experimental results on three benchmark datasets demonstrate the effectiveness and robustness of KRDN over the state-of-the-art knowledge-aware methods like KGIN, MCCLK, and KGCL, and also outperform robust recommendation models like SGL and SimGCL.

References in corpus (29)

• Adam: A Method for Stochastic Optimization
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Categorical Reparameterization with Gumbel-Softmax
• Neural Graph Collaborative Filtering
• KGAT: Knowledge Graph Attention Network for Recommendation
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Self-supervised Graph Learning for Recommendation
• Simplifying Graph Convolutional Networks
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
• Knowledge Graph Convolutional Networks for Recommender Systems
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning
• Knowledge Graph Contrastive Learning for Recommendation
• Learning over Knowledge-Base Embeddings for Recommendation
• Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Denoising Implicit Feedback for Recommendation
• Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
• DKN: Deep Knowledge-Aware Network for News Recommendation
• MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation
• Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation
• Self-Guided Learning to Denoise for Robust Recommendation
• Learning Robust Recommenders through Cross-Model Agreement
• ATBRG: Adaptive Target-Behavior Relational Graph Network for Effective Recommendation
• SimpleX: A Simple and Strong Baseline for Collaborative Filtering
• DisARM: An Antithetic Gradient Estimator for Binary Latent Variables
• Towards Explainable Collaborative Filtering with Taste Clusters Learning
• HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation

Cited by in corpus (3)

• Comprehending Knowledge Graphs with Large Language Models for Recommender Systems
• Unleashing the Power of Large Language Model for Denoising Recommendation
• Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing