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 (10)

• Adam: A Method for Stochastic Optimization
• Neural Machine Translation by Jointly Learning to Align and Translate
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Variational Graph Auto-Encoders
• A Neural Autoregressive Approach to Collaborative Filtering
• Matrix Completion on Graphs
• Neural Network Matrix Factorization
• Provable Inductive Matrix Completion

Cited by in corpus (231)

• A Comprehensive Survey on Graph Neural Networks
• KGAT: Knowledge Graph Attention Network for Recommendation
• Deep Learning based Recommender System: A Survey and New Perspectives
• Graph Neural Networks: A Review of Methods and Applications
• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Knowledge Graph Contrastive Learning for Recommendation
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• A Comprehensive Survey on Deep Graph Representation Learning
• FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
• Attention-based Graph Neural Network for Semi-supervised Learning
• Federated Social Recommendation with Graph Neural Network
• Stochastic Training of Graph Convolutional Networks with Variance Reduction
• Knowledge Graph Self-Supervised Rationalization for Recommendation
• A Review-aware Graph Contrastive Learning Framework for Recommendation
• GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment
• DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation
• Deep Learning on Graphs: A Survey
• DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation
• DGCN: Diversified Recommendation with Graph Convolutional Networks
• Learning on Attribute-Missing Graphs
• Automated Self-Supervised Learning for Recommendation
• Multi-view Intent Disentangle Graph Networks for Bundle Recommendation
• Session-based Recommendation with Hypergraph Attention Networks
• Adaptive Propagation Graph Convolutional Network
• Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• Compositional Fairness Constraints for Graph Embeddings
• Handling Missing Data with Graph Representation Learning
• Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks
• SocialGCN: An Efficient Graph Convolutional Network based Model for Social Recommendation
• Graph Convolution Machine for Context-aware Recommender System
• Representation Learning for Natural Language Processing
• GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems
• Residual Correlation in Graph Neural Network Regression
• Deep Models of Interactions Across Sets
• MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering
• MedGCN: Medication recommendation and lab test imputation via graph convolutional networks
• Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering
• Graph Neural Networks for Social Recommendation
• Dual Space Graph Contrastive Learning
• Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs
• Graph-less Collaborative Filtering
• Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering for Recommendation
• GIF: A General Graph Unlearning Strategy via Influence Function
• STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
• MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation
• DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation
• Contrastive Learning for Recommender System
• GDSRec: Graph-Based Decentralized Collaborative Filtering for Social Recommendation
• Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds
• AEGCN: An Autoencoder-Constrained Graph Convolutional Network
• GLocal-K: Global and Local Kernels for Recommender Systems
• Sparse Sampling for Inverse Problems with Tensors
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
• Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
• Graph Representation Learning for Road Type Classification
• Graph neural network-based fault diagnosis: a review
• Natural Graph Networks
• UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation
• Real-time Seismic Intensity Prediction using Self-supervised Contrastive GNN for Earthquake Early Warning
• Graph Collaborative Reasoning
• Graph Neural Networks: Methods, Applications, and Opportunities
• Inductive Matrix Completion Based on Graph Neural Networks
• Stochastic Graph Neural Networks
• Recent Advances in Heterogeneous Relation Learning for Recommendation
• A Review of Graph Neural Networks and Their Applications in Power Systems
• Distributed Training of Graph Convolutional Networks
• Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
• Data Imputation with Iterative Graph Reconstruction
• Improving Graph Attention Networks with Large Margin-based Constraints
• A literature survey of matrix methods for data science
• Hybrid Quantum-Classical Graph Convolutional Network
• Binarized Collaborative Filtering with Distilling Graph Convolutional Networks
• What graph neural networks cannot learn: depth vs width
• Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
• SimpleX: A Simple and Strong Baseline for Collaborative Filtering
• Decimated Framelet System on Graphs and Fast G-Framelet Transforms
• INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
• Degree-Quant: Quantization-Aware Training for Graph Neural Networks
• Sequential Recommendation with Graph Neural Networks
• Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
• Combining social relations and interaction data in Recommender System with Graph Convolution Collaborative Filtering
• On Provable Benefits of Depth in Training Graph Convolutional Networks
• How hard is to distinguish graphs with graph neural networks?
• Graph Sampling for Matrix Completion Using Recurrent Gershgorin Disc Shift
• User Consented Federated Recommender System Against Personalized Attribute Inference Attack
• Improving Graph Neural Networks with Simple Architecture Design
• Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks
• Relational Generalized Few-Shot Learning
• NGAT4Rec: Neighbor-Aware Graph Attention Network For Recommendation
• Joint Item Recommendation and Attribute Inference: An Adaptive Graph Convolutional Network Approach
• Named Entity Disambiguation using Deep Learning on Graphs
• Bundle Recommendation with Graph Convolutional Networks
• Graph Learning Network: A Structure Learning Algorithm
• Explicit Feature Interaction-aware Graph Neural Networks
• Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
• Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information
• Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering
• Collaborative Reflection-Augmented Autoencoder Network for Recommender Systems
• A Light Heterogeneous Graph Collaborative Filtering Model using Textual Information
• Revisiting Neighborhood-based Link Prediction for Collaborative Filtering
• BasConv: Aggregating Heterogeneous Interactions for Basket Recommendation with Graph Convolutional Neural Network
• General Partial Label Learning via Dual Bipartite Graph Autoencoder
• Socially-Aware Self-Supervised Tri-Training for Recommendation
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Graph Learning based Recommender Systems: A Review
• RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation
• Context-Aware Visual Compatibility Prediction
• Inhomogeneous Social Recommendation with Hypergraph Convolutional Networks
• Rubik: A Hierarchical Architecture for Efficient Graph Learning
• Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
• Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems
• A Survey of Latent Factor Models in Recommender Systems
• Robust Basket Recommendation via Noise-tolerated Graph Contrastive Learning
• Multi-Component Graph Convolutional Collaborative Filtering
• Neural IR Meets Graph Embedding: A Ranking Model for Product Search
• GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection
• Information Obfuscation of Graph Neural Networks
• A Robust Hierarchical Graph Convolutional Network Model for Collaborative Filtering
• Network In Graph Neural Network
• Multi-Graph based Multi-Scenario Recommendation in Large-scale Online Video Services
• Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer
• Deconvolutional Networks on Graph Data
• Graph-Revised Convolutional Network
• Deoscillated Graph Collaborative Filtering
• Regional based query in graph active learning
• LT-OCF: Learnable-Time ODE-based Collaborative Filtering
• Graph-Aware Transformer: Is Attention All Graphs Need?
• Convolutional Geometric Matrix Completion
• Learning Stochastic Graph Neural Networks with Constrained Variance
• Sparse Graph Attention Networks
• Item Graph Convolution Collaborative Filtering for Inductive Recommendations
• Bipartite Graph Embedding via Mutual Information Maximization
• Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach
• Price-aware Recommendation with Graph Convolutional Networks
• 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 Autoencoders with Deconvolutional Networks
• Metapath- and Entity-aware Graph Neural Network for Recommendation
• Learning to Cluster Faces via Confidence and Connectivity Estimation
• Deep Graph Library Optimizations for Intel(R) x86 Architecture
• Pairwise Interactive Graph Attention Network for Context-Aware Recommendation
• GMLP: Building Scalable and Flexible Graph Neural Networks with Feature-Message Passing
• Prototypical Contrastive Learning through Alignment and Uniformity for Recommendation
• Spectral Geometric Matrix Completion
• Highly Accurate Disease Diagnosis and Highly Reproducible Biomarker Identification with PathFormer
• Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN
• Heterogeneous Graph Collaborative Filtering
• Hop-Hop Relation-aware Graph Neural Networks
• Application of Knowledge Graphs to Provide Side Information for Improved Recommendation Accuracy
• Neural Message Passing for Objective-Based Uncertainty Quantification and Optimal Experimental Design
• DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability
• DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• Basket Recommendation with Multi-Intent Translation Graph Neural Network
• div2vec: Diversity-Emphasized Node Embedding
• Geometric Matrix Completion: A Functional View
• Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
• Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network
• Matrix Completion With Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference
• Inferring Javascript types using Graph Neural Networks
• Extendable Neural Matrix Completion
• Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative Filtering
• Determinable and interpretable network representation for link prediction
• Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks
• Multi-Graph Convolution Collaborative Filtering
• Simulating Execution Time of Tensor Programs using Graph Neural Networks
• BayReL: Bayesian Relational Learning for Multi-omics Data Integration
• Edge-Enhanced Global Disentangled Graph Neural Network for Sequential Recommendation
• A^2-GCN: An Attribute-aware Attentive GCN Model for Recommendation
• Graph Highway Networks
• A Biased Graph Neural Network Sampler with Near-Optimal Regret
• User Embedding based Neighborhood Aggregation Method for Inductive Recommendation
• PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
• Multi-Sample based Contrastive Loss for Top-k Recommendation
• Graph Attention Collaborative Similarity Embedding for Recommender System
• Dynamic Graph Collaborative Filtering
• Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph
• Group-Buying Recommendation for Social E-Commerce
• Hop Sampling: A Simple Regularized Graph Learning for Non-Stationary Environments
• Interest-aware Message-Passing GCN for Recommendation
• Dual Side Deep Context-aware Modulation for Social Recommendation
• Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation
• Graph Learning Augmented Heterogeneous Graph Neural Network for Social Recommendation
• Multi-output Gaussian Processes for Uncertainty-aware Recommender Systems
• UserReg: A Simple but Strong Model for Rating Prediction
• Res-GCNN: A Lightweight Residual Graph Convolutional Neural Networks for Human Trajectory Forecasting
• Dynamic Sequential Graph Learning for Click-Through Rate Prediction
• Matrix Decomposition on Graphs: A Functional View
• Classifying the Cosmic-Ray Proton and Light Groups on the LHAASO-KM2A Experiment with the Graph Neural Network
• SceneRec: Scene-Based Graph Neural Networks for Recommender Systems
• Temporal Network Representation Learning via Historical Neighborhoods Aggregation
• Linear, or Non-Linear, That is the Question!
• Deep Social Collaborative Filtering
• Personalized Hashtag Recommendation for Micro-videos
• Advances in Collaborative Filtering and Ranking
• On the Importance of Sampling in Training GCNs: Tighter Analysis and Variance Reduction
• Into the Battlefield: Quantifying and Modeling Intra-community Conflicts in Online Discussion
• printf: Preference Modeling Based on User Reviews with Item Images and Textual Information via Graph Learning
• EfficientRec an unlimited user-item scale recommendation system based on clustering and users interaction embedding profile
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees
• How Powerful is Graph Convolution for Recommendation?
• Inductive Matrix Completion Using Graph Autoencoder
• Improving One-class Recommendation with Multi-tasking on Various Preference Intensities
• SocialTrans: A Deep Sequential Model with Social Information for Web-Scale Recommendation Systems
• Scalable Recommender Systems through Recursive Evidence Chains
• Network Representation Learning: From Traditional Feature Learning to Deep Learning
• Quaternion-Based Graph Convolution Network for Recommendation
• Pre-training Recommender Systems via Reinforced Attentive Multi-relational Graph Neural Network
• Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
• Exploration-Exploitation Motivated Variational Auto-Encoder for Recommender Systems
• Dual Graph Embedding for Object-Tag LinkPrediction on the Knowledge Graph
• Bipartite Link Prediction based on Topological Features via 2-hop Path
• Hierarchical BiGraph Neural Network as Recommendation Systems
• Grouping Search Results with Product Graphs in E-commerce Platforms
• DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition
• GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback
• CoRGi: Content-Rich Graph Neural Networks with Attention
• Global Context Enhanced Social Recommendation with Hierarchical Graph Neural Networks
• A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps
• Dual Graph enhanced Embedding Neural Network for CTR Prediction
• Temporal Graph Offset Reconstruction: Towards Temporally Robust Graph Representation Learning
• Revisiting SVD to generate powerful Node Embeddings for Recommendation Systems
• Spectrum-enhanced Pairwise Learning to Rank
• A Behavior-aware Graph Convolution Network Model for Video Recommendation
• Graph-based Multilingual Product Retrieval in E-commerce Search
• Anomaly Detection for Aggregated Data Using Multi-Graph Autoencoder
• Structure-Aware Face Clustering on a Large-Scale Graph with $10^7$ Nodes