Neural Graph Collaborative Filtering

Abstract

Learning vector representations (aka. embeddings) of users and items lies at the core of modern recommender systems. Ranging from early matrix factorization to recently emerged deep learning based methods, existing efforts typically obtain a user's (or an item's) embedding by mapping from pre-existing features that describe the user (or the item), such as ID and attributes. We argue that an inherent drawback of such methods is that, the collaborative signal, which is latent in user-item interactions, is not encoded in the embedding process. As such, the resultant embeddings may not be sufficient to capture the collaborative filtering effect. In this work, we propose to integrate the user-item interactions -- more specifically the bipartite graph structure -- into the embedding process. We develop a new recommendation framework Neural Graph Collaborative Filtering (NGCF), which exploits the user-item graph structure by propagating embeddings on it. This leads to the expressive modeling of high-order connectivity in user-item graph, effectively injecting the collaborative signal into the embedding process in an explicit manner. We conduct extensive experiments on three public benchmarks, demonstrating significant improvements over several state-of-the-art models like HOP-Rec and Collaborative Memory Network. Further analysis verifies the importance of embedding propagation for learning better user and item representations, justifying the rationality and effectiveness of NGCF. Codes are available at https://github.com/xiangwang1223/neural_graph_collaborative_filtering.

SIGIR 2019; the latest version of NGCF paper, which is distinct from the version published in ACM Digital Library

References in corpus (12)

• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• KGAT: Knowledge Graph Attention Network for Recommendation
• Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering
• Representation Learning on Graphs with Jumping Knowledge Networks
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
• DeepInf: Social Influence Prediction with Deep Learning
• Adversarial Personalized Ranking for Recommendation
• Collaborative Memory Network for Recommendation Systems
• Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews
• Latent Relational Metric Learning via Memory-based Attention for Collaborative Ranking
• Item Silk Road: Recommending Items from Information Domains to Social Users
• Spectral Collaborative Filtering

Cited by in corpus (253)

• KGAT: Knowledge Graph Attention Network for Recommendation
• Self-supervised Graph Learning for Recommendation
• FedKD: Communication Efficient Federated Learning via Knowledge Distillation
• Disentangled Graph Collaborative Filtering
• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning
• Global Context Enhanced Graph Neural Networks for Session-based Recommendation
• Hypergraph Contrastive Collaborative Filtering
• Causal Intervention for Leveraging Popularity Bias in Recommendation
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• Intent Contrastive Learning for Sequential Recommendation
• Mining Latent Structures for Multimedia Recommendation
• When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
• A Comprehensive Survey on Deep Graph Representation Learning
• FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
• Denoising Implicit Feedback for Recommendation
• Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System
• Heterogeneous Graph Contrastive Learning for Recommendation
• Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
• Multi-Modal Self-Supervised Learning for Recommendation
• Graph Meta Network for Multi-Behavior Recommendation
• Representation Learning with Large Language Models for Recommendation
• Contrastive Meta Learning with Behavior Multiplicity for Recommendation
• Towards Representation Alignment and Uniformity in Collaborative Filtering
• Federated Social Recommendation with Graph Neural Network
• Multi-View Graph Convolutional Network for Multimedia Recommendation
• Knowledge Graph Self-Supervised Rationalization for Recommendation
• Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue
• DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation
• Deconfounded Recommendation for Alleviating Bias Amplification
• Reinforced Negative Sampling over Knowledge Graph for Recommendation
• Interactive Path Reasoning on Graph for Conversational Recommendation
• Self-Supervised Hypergraph Transformer for Recommender Systems
• Disentangled Contrastive Collaborative Filtering
• Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network
• Graph Enhanced Representation Learning for News Recommendation
• DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation
• DGCN: Diversified Recommendation with Graph Convolutional Networks
• Automated Self-Supervised Learning for Recommendation
• CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
• Social Recommendation with Self-Supervised Metagraph Informax Network
• MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation
• Learning to Recommend with Multiple Cascading Behaviors
• Multi-Behavior Recommendation with Cascading Graph Convolution Networks
• Knowledge Enhancement for Contrastive Multi-Behavior Recommendation
• CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
• GAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendation
• Elliot: a Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluation
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment
• Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users
• SelfCF: A Simple Framework for Self-supervised Collaborative Filtering
• DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
• Heterogeneous Graph Representation Learning with Relation Awareness
• Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks
• Graph Transformer for Recommendation
• Graph Convolution Machine for Context-aware Recommender System
• Multi-Behavior Enhanced Recommendation with Cross-Interaction Collaborative Relation Modeling
• Multi-behavior Self-supervised Learning for Recommendation
• Multi-Behavior Sequential Recommendation with Temporal Graph Transformer
• Self-Guided Learning to Denoise for Robust Recommendation
• FedRecAttack: Model Poisoning Attack to Federated Recommendation
• Toward Pareto Efficient Fairness-Utility Trade-off inRecommendation through Reinforcement Learning
• GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems
• HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization
• Market2Dish: Health-aware Food Recommendation
• Multi-Behavior Graph Neural Networks for Recommender System
• On the Effectiveness of Sampled Softmax Loss for Item Recommendation
• Collaboration-Aware Graph Convolutional Network for Recommender Systems
• How to Retrain Recommender System? A Sequential Meta-Learning Method
• Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering
• MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering
• Learning Graph ODE for Continuous-Time Sequential Recommendation
• Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
• Learning Robust Recommenders through Cross-Model Agreement
• Large-scale Personalized Video Game Recommendation via Social-aware Contextualized Graph Neural Network
• RecDCL: Dual Contrastive Learning for Recommendation
• Modeling Two-Way Selection Preference for Person-Job Fit
• One for All, All for One: Learning and Transferring User Embeddings for Cross-Domain Recommendation
• Time Interval-enhanced Graph Neural Network for Shared-account Cross-domain Sequential Recommendation
• HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework
• Meta-optimized Contrastive Learning for Sequential Recommendation
• HICF: Hyperbolic Informative Collaborative Filtering
• Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering for Recommendation
• GIF: A General Graph Unlearning Strategy via Influence Function
• HS-GCN: Hamming Spatial Graph Convolutional Networks for Recommendation
• AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
• MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation
• Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
• Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering
• Invariant Collaborative Filtering to Popularity Distribution Shift
• FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
• Parallel Knowledge Enhancement based Framework for Multi-behavior Recommendation
• Thinking inside The Box: Learning Hypercube Representations for Group Recommendation
• Knowledge-enhanced Black-box Attacks for Recommendations
• Learning to Ask Appropriate Questions in Conversational Recommendation
• GDSRec: Graph-Based Decentralized Collaborative Filtering for Social Recommendation
• Neural Graph Matching based Collaborative Filtering
• Multi-level Contrastive Learning Framework for Sequential Recommendation
• A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges
• Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendation
• RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network
• Formalizing Multimedia Recommendation through Multimodal Deep Learning
• On the User Behavior Leakage from Recommender System Exposure
• Knowledge-refined Denoising Network for Robust Recommendation
• Dynamically Expandable Graph Convolution for Streaming Recommendation
• Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
• SIGformer: Sign-aware Graph Transformer for Recommendation
• Graph Collaborative Reasoning
• CatGCN: Graph Convolutional Networks with Categorical Node Features
• CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process
• Adap-$\tau$: Adaptively Modulating Embedding Magnitude for Recommendation
• Multi-domain Recommendation with Embedding Disentangling and Domain Alignment
• Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation
• Widespread Flaws in Offline Evaluation of Recommender Systems
• Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
• Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering
• Personality-Driven Social Multimedia Content Recommendation
• Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
• Augmented Negative Sampling for Collaborative Filtering
• DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
• Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation
• Leveraging Two Types of Global Graph for Sequential Fashion Recommendation
• Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation
• RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendation
• A Comprehensive Survey on Self-Supervised Learning for Recommendation
• Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks
• Graph-based Alignment and Uniformity for Recommendation
• INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
• Bipartite Graph Convolutional Hashing for Effective and Efficient Top-N Search in Hamming Space
• Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation
• Local Collaborative Autoencoders
• Transition Propagation Graph Neural Networks for Temporal Networks
• LightGNN: Simple Graph Neural Network for Recommendation
• Predicting Information Pathways Across Online Communities
• GraFN: Semi-Supervised Node Classification on Graph with Few Labels via Non-Parametric Distribution Assignment
• Combining social relations and interaction data in Recommender System with Graph Convolution Collaborative Filtering
• Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling
• Adaptive Collaborative Filtering with Personalized Time Decay Functions for Financial Product Recommendation
• User Consented Federated Recommender System Against Personalized Attribute Inference Attack
• M2GNN: Metapath and Multi-interest Aggregated Graph Neural Network for Tag-based Cross-domain Recommendation
• Beyond NDCG: behavioral testing of recommender systems with RecList
• Towards Robust Recommendation via Decision Boundary-aware Graph Contrastive Learning
• Long-Tail Session-based Recommendation from Calibration
• Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning
• HIEN: Hierarchical Intention Embedding Network for Click-Through Rate Prediction
• Learning Backward Compatible Embeddings
• Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis
• Quaternion-Based Self-Attentive Long Short-Term User Preference Encoding for Recommendation
• Pareto Invariant Representation Learning for Multimedia Recommendation
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
• OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining
• Content-Based Collaborative Generation for Recommender Systems
• Code Recommendation for Open Source Software Developers
• Recommending on graphs: a comprehensive review from a data perspective
• Toward a Better Understanding of Loss Functions for Collaborative Filtering
• Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System
• JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks
• Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering
• A Multi-Channel Next POI Recommendation Framework with Multi-Granularity Check-in Signals
• Integrating Item Relevance in Training Loss for Sequential Recommender Systems
• A Light Heterogeneous Graph Collaborative Filtering Model using Textual Information
• Collaborative Reflection-Augmented Autoencoder Network for Recommender Systems
• Task Relation-aware Continual User Representation Learning
• Revisiting Neighborhood-based Link Prediction for Collaborative Filtering
• Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis
• Exploring Lottery Ticket Hypothesis in Media Recommender Systems
• History-Augmented Collaborative Filtering for Financial Recommendations
• Dual Policy Learning for Aggregation Optimization in Graph Neural Network-based Recommender Systems
• STGIN: Spatial-Temporal Graph Interaction Network for Large-scale POI Recommendation
• Graph Neural Bandits
• Unlocking the Hidden Treasures: Enhancing Recommendations with Unlabeled Data
• Learning and Optimization of Implicit Negative Feedback for Industrial Short-video Recommender System
• Heterogeneous Information Network-based Interest Composition with Graph Neural Network for Recommendation
• Fair Augmentation for Graph Collaborative Filtering
• Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation
• Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems
• Modeling Dual Period-Varying Preferences for Takeaway Recommendation
• LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture
• MixRec: Individual and Collective Mixing Empowers Data Augmentation for Recommender Systems
• Towards Lightweight Cross-domain Sequential Recommendation via External Attention-enhanced Graph Convolution Network
• Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System
• LogicRec: Recommendation with Users' Logical Requirements
• CombiGCN: An effective GCN model for Recommender System
• LightSAGE: Graph Neural Networks for Large Scale Item Retrieval in Shopee's Advertisement Recommendation
• Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems
• Heterogeneous Hyper-Graph Neural Networks for Context-aware Human Activity Recognition
• Robust Basket Recommendation via Noise-tolerated Graph Contrastive Learning
• Debiased Graph Poisoning Attack via Contrastive Surrogate Objective
• Preventing the Popular Item Embedding Based Attack in Federated Recommendations
• Personalized Image Generation with Large Multimodal Models
• HGCH: A Hyperbolic Graph Convolution Network Model for Heterogeneous Collaborative Graph Recommendation
• Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning
• GraphFM: Graph Factorization Machines for Feature Interaction Modeling
• BeLightRec: A lightweight recommender system enhanced with BERT
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
• Stock Recommendations for Individual Investors: A Temporal Graph Network Approach with Mean-Variance Efficient Sampling
• GradCraft: Elevating Multi-task Recommendations through Holistic Gradient Crafting
• Eco-Aware Graph Neural Networks for Sustainable Recommendations
• Mitigating Spurious Correlations for Self-supervised Recommendation
• CROLoss: Towards a Customizable Loss for Retrieval Models in Recommender Systems
• Graph-Sequential Alignment and Uniformity: Toward Enhanced Recommendation Systems
• Consistency and Discrepancy-Based Contrastive Tripartite Graph Learning for Recommendations
• Cross-Domain Latent Factors Sharing via Implicit Matrix Factorization
• Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach
• Item Graph Convolution Collaborative Filtering for Inductive Recommendations
• Unbiased and Robust: External Attention-enhanced Graph Contrastive Learning for Cross-domain Sequential Recommendation
• Collaborative Residual Metric Learning
• S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domain
• Fine-tuning Partition-aware Item Similarities for Efficient and Scalable Recommendation
• In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems
• Prototypical Contrastive Learning through Alignment and Uniformity for Recommendation
• Lightweight yet Efficient: An External Attentive Graph Convolutional Network with Positional Prompts for Sequential Recommendation
• Rankformer: A Graph Transformer for Recommendation based on Ranking Objective
• Popularity Debiasing from Exposure to Interaction in Collaborative Filtering
• Unified Dual-Intent Translation for Joint Modeling of Search and Recommendation
• Intent Propagation Contrastive Collaborative Filtering
• A Worrying Reproducibility Study of Intent-Aware Recommendation Models
• Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation
• A Vlogger-augmented Graph Neural Network Model for Micro-video Recommendation
• Network-Based Video Recommendation Using Viewing Patterns and Modularity Analysis: An Integrated Framework
• Rolling Forward: Enhancing LightGCN with Causal Graph Convolution for Credit Bond Recommendation
• XInsight: Revealing Model Insights for GNNs with Flow-based Explanations
• It's Enough: Relaxing Diagonal Constraints in Linear Autoencoders for Recommendation
• DLF: Enhancing Explicit-Implicit Interaction via Dynamic Low-Order-Aware Fusion for CTR Prediction
• Determinable and interpretable network representation for link prediction
• Collaborative Diffusion Model for Recommender System
• Rethinking Conversational Recommendations: Is Decision Tree All You Need?
• Pre-training for Recommendation Unlearning
• X-Cross: Dynamic Integration of Language Models for Cross-Domain Sequential Recommendation
• SEP-GCN: Leveraging Similar Edge Pairs with Temporal and Spatial Contexts for Location-Based Recommender Systems
• Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing
• Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation
• VM-Rec: A Variational Mapping Approach for Cold-start User Recommendation
• Cyberswarm: a novel swarm intelligence algorithm inspired by cyber community dynamics
• FedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal Decoupling
• HEAT: A Highly Efficient and Affordable Training System for Collaborative Filtering Based Recommendation on CPUs
• Evaluating and Addressing Fairness Across User Groups in Negative Sampling for Recommender Systems
• Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users
• Generative Data Augmentation in Graph Contrastive Learning for Recommendation
• Pure Spectral Graph Embeddings: Reinterpreting Graph Convolution for Top-N Recommendation
• Recommendation and Temptation
• Graph-based Recommendation for Sparse and Heterogeneous User Interactions
• Improving One-class Recommendation with Multi-tasking on Various Preference Intensities
• Category-based and Popularity-guided Video Game Recommendation: A Balance-oriented Framework
• printf: Preference Modeling Based on User Reviews with Item Images and Textual Information via Graph Learning
• Hessian-aware Quantized Node Embeddings for Recommendation
• Mean-Variance Efficient Collaborative Filtering for Stock Recommendation
• Recommendation Fairness in Social Networks Over Time
• Exploiting Preferences in Loss Functions for Sequential Recommendation via Weak Transitivity
• Scalable Personalised Item Ranking through Parametric Density Estimation
• A Transfer Framework for Enhancing Temporal Graph Learning in Data-Scarce Settings
• A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring
• I${}^3$-MRec: Invariant Learning with Information Bottleneck for Incomplete Modality Recommendation