Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System

Abstract

Knowledge graph (KG) plays an increasingly important role in recommender systems. Recently, graph neural networks (GNNs) based model has gradually become the theme of knowledge-aware recommendation (KGR). However, there is a natural deficiency for GNN-based KGR models, that is, the sparse supervised signal problem, which may make their actual performance drop to some extent. Inspired by the recent success of contrastive learning in mining supervised signals from data itself, in this paper, we focus on exploring the contrastive learning in KG-aware recommendation and propose a novel multi-level cross-view contrastive learning mechanism, named MCCLK. Different from traditional contrastive learning methods which generate two graph views by uniform data augmentation schemes such as corruption or dropping, we comprehensively consider three different graph views for KG-aware recommendation, including global-level structural view, local-level collaborative and semantic views. Specifically, we consider the user-item graph as a collaborative view, the item-entity graph as a semantic view, and the user-item-entity graph as a structural view. MCCLK hence performs contrastive learning across three views on both local and global levels, mining comprehensive graph feature and structure information in a self-supervised manner. Besides, in semantic view, a k-Nearest-Neighbor (kNN) item-item semantic graph construction module is proposed, to capture the important item-item semantic relation which is usually ignored by previous work. Extensive experiments conducted on three benchmark datasets show the superior performance of our proposed method over the state-of-the-arts. The implementations are available at: https://github.com/CCIIPLab/MCCLK.

arXiv commentAccepted to SIGIR2022

References in corpus (24)

• Adam: A Method for Stochastic Optimization
• A Simple Framework for Contrastive Learning of Visual Representations
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Neural Graph Collaborative Filtering
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• KGAT: Knowledge Graph Attention Network for Recommendation
• Self-supervised Graph Learning for Recommendation
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
• Graph Contrastive Learning with Adaptive Augmentation
• xDeepFM: Combining Explicit and Implicit Feature Interactions 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
• Global Context Enhanced Graph Neural Networks for Session-based Recommendation
• Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Deep Graph Contrastive Representation Learning
• Contrastive Multi-View Representation Learning on Graphs
• Mining Latent Structures for Multimedia Recommendation
• SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• DKN: Deep Knowledge-Aware Network for News Recommendation
• Multi-view Intent Disentangle Graph Networks for Bundle Recommendation
• Hierarchical Attentive Knowledge Graph Embedding for Personalized Recommendation

Cited by in corpus (14)

• Knowledge Graph Self-Supervised Rationalization for Recommendation
• Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning
• Multi-level Contrastive Learning Framework for Sequential Recommendation
• VRKG4Rec: Virtual Relational Knowledge Graphs for Recommendation
• Knowledge-refined Denoising Network for Robust Recommendation
• Knowledge Enhanced Multi-intent Transformer Network for Recommendation
• A Comprehensive Survey on Self-Supervised Learning for Recommendation
• Improving Personality Consistency in Conversation by Persona Extending
• LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture
• RecKG: Knowledge Graph for Recommender Systems
• LogicRec: Recommendation with Users' Logical Requirements
• Contrastive Learning on Medical Intents for Sequential Prescription Recommendation
• Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing
• FedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal Decoupling