Graph Convolutional Matrix Completion

Abstract

We consider matrix completion for recommender systems from the point of view of link prediction on graphs. Interaction data such as movie ratings can be represented by a bipartite user-item graph with labeled edges denoting observed ratings. Building on recent progress in deep learning on graph-structured data, we propose a graph auto-encoder framework based on differentiable message passing on the bipartite interaction graph. Our model shows competitive performance on standard collaborative filtering benchmarks. In settings where complimentary feature information or structured data such as a social network is available, our framework outperforms recent state-of-the-art methods.

9 pages, 3 figures, updated with additional experimental evaluation

References in corpus (3)

• Semi-Supervised Classification with Graph Convolutional Networks
• Variational Graph Auto-Encoders
• Matrix Completion on Graphs

Cited by in corpus (66)

• KGAT: Knowledge Graph Attention Network for Recommendation
• Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works
• Compositional Fairness Constraints for Graph Embeddings
• Representation Learning for Natural Language Processing
• GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems
• Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering
• STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
• Contrastive Learning for Recommender System
• Improving Graph Attention Networks with Large Margin-based Constraints
• Binarized Collaborative Filtering with Distilling Graph Convolutional Networks
• Hybrid Quantum-Classical Graph Convolutional Network
• Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
• Bundle Recommendation with Graph Convolutional Networks
• Joint Item Recommendation and Attribute Inference: An Adaptive Graph Convolutional Network Approach
• Graph Learning Network: A Structure Learning Algorithm
• Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
• Context-Aware Visual Compatibility Prediction
• RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation
• Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
• Rubik: A Hierarchical Architecture for Efficient Graph Learning
• Neural IR Meets Graph Embedding: A Ranking Model for Product Search
• GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection
• Multi-Component Graph Convolutional Collaborative Filtering
• A Robust Hierarchical Graph Convolutional Network Model for Collaborative Filtering
• Regional based query in graph active learning
• Bipartite Graph Embedding via Mutual Information Maximization
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• Non-Parametric Graph Learning for Bayesian Graph Neural Networks
• Graph-Aware Transformer: Is Attention All Graphs Need?
• Deep Graph Library Optimizations for Intel(R) x86 Architecture
• GMLP: Building Scalable and Flexible Graph Neural Networks with Feature-Message Passing
• Graph Autoencoders with Deconvolutional Networks
• Pairwise Interactive Graph Attention Network for Context-Aware Recommendation
• Learning to Cluster Faces via Confidence and Connectivity Estimation
• Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative Filtering
• Application of Knowledge Graphs to Provide Side Information for Improved Recommendation Accuracy
• Geometric Matrix Completion: A Functional View
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• div2vec: Diversity-Emphasized Node Embedding
• Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network
• Hop-Hop Relation-aware Graph Neural Networks
• Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
• Inferring Javascript types using Graph Neural Networks
• PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
• Multi-Graph Convolution Collaborative Filtering
• Graph Highway Networks
• User Embedding based Neighborhood Aggregation Method for Inductive Recommendation
• Graph Attention Collaborative Similarity Embedding for Recommender System
• Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation
• Dual Side Deep Context-aware Modulation for Social Recommendation
• UserReg: A Simple but Strong Model for Rating Prediction
• Hop Sampling: A Simple Regularized Graph Learning for Non-Stationary Environments
• Matrix Decomposition on Graphs: A Functional View
• Dynamic Graph Collaborative Filtering
• Classifying the Cosmic-Ray Proton and Light Groups on the LHAASO-KM2A Experiment with the Graph Neural Network
• Interest-aware Message-Passing GCN for Recommendation
• Advances in Collaborative Filtering and Ranking
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees
• SceneRec: Scene-Based Graph Neural Networks for Recommender Systems
• Deep Social Collaborative Filtering
• Network Representation Learning: From Traditional Feature Learning to Deep Learning
• Spectrum-enhanced Pairwise Learning to Rank
• SocialTrans: A Deep Sequential Model with Social Information for Web-Scale Recommendation Systems
• Dual Graph Embedding for Object-Tag LinkPrediction on the Knowledge Graph
• Structure-Aware Face Clustering on a Large-Scale Graph with $10^7$ Nodes
• Hierarchical BiGraph Neural Network as Recommendation Systems