LightGCN

2020/07/25 by Xiangnan He, Kuan Deng, Xiang Wang +3 · 132 citations
Computer Science · #Advanced Graph Neural Networks #Image and Video Quality Assessment #Recommender Systems and Techniques

paper · doi:10.1145/3397271.3401063

openalex publication_date 2020/07/25 · openalex created_date 2020/07/29 · openalex updated_date 2026/07/31

Abstract

Graph Convolution Network (GCN) has become new state-of-the-art for collaborative filtering. Nevertheless, the reasons of its effectiveness for recommendation are not well understood. Existing work that adapts GCN to recommendation lacks thorough ablation analyses on GCN, which is originally designed for graph classification tasks and equipped with many neural network operations. However, we empirically find that the two most common designs in GCNs -- feature transformation and nonlinear activation -- contribute little to the performance of collaborative filtering. Even worse, including them adds to the difficulty of training and degrades recommendation performance.

Citations

• Matrix Factorization Techniques for Recommender Systems
• Temporal Relational Ranking for Stock Prediction

Cited by

• Latent Structure Mining With Contrastive Modality Fusion for Multimedia Recommendation
• Reinforcement Learning-enhanced Shared-account Cross-domain Sequential Recommendation
• Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation
• Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning
• CoLLM: Integrating Collaborative Embeddings Into Large Language Models for Recommendation
• ExplainRec: Towards Explainable Multi-Modal Zero-Shot Recommendation with Preference Attribution and Large Language Models
• PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion
• Sequential Recommendation with Graph Neural Networks
• LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains
• How Can Recommender Systems Benefit from Large Language Models: A Survey
• Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
• TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation
• Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
• Inductive Transfer Learning for Graph-Based Recommenders
• Disentangling User Interest and Conformity for Recommendation with Causal Embedding
• Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation
• LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems
• Enhancing Graph Neural Networks: A Mutual Learning Approach
• Unifying Inductive, Cross-Domain, and Multimodal Learning for Robust and Generalizable Recommendation
• Inductive Matrix Completion Using Graph Autoencoder
• A Simulation Framework for Studying Systemic Effects of Feedback Loops in Recommender Systems
• Causality Enhancement for Cross-Domain Recommendation
• A Critical Study on Data Leakage in Recommender System Offline Evaluation
• Graph Learning based Recommender Systems: A Review
• Density-Ratio Based Personalised Ranking from Implicit Feedback
• Causal Inspired Multi Modal Recommendation
• Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs
• Aligning Language Models with Investor and Market Behavior for Financial Recommendations
• MIARec: Mutual-influence-aware Heterogeneous Network Embedding for Scientific Paper Recommendation
• Post-hoc Popularity Bias Correction in GNN-based Collaborative Filtering
• Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
• Lighter-X: An Efficient and Plug-and-play Strategy for Graph-based Recommendation through Decoupled Propagation
• Multi-View Graph Learning with Graph-Tuple
• Generative Data Augmentation in Graph Contrastive Learning for Recommendation
• Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation
• MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation
• Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations
• AgentDR Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents
• Reproducibility Study of "XRec: Large Language Models for Explainable Recommendation"
• Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation
• Harnessing LLM for Noise-Robust Cognitive Diagnosis in Web-Based Intelligent Education Systems
• LightMove: A Lightweight Next-POI Recommendation for Taxicab Rooftop Advertising
• Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Experts
• Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation
• SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction
• SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems
• SimpleX: A Simple and Strong Baseline for Collaborative Filtering
• A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning
• GoalRank: Group-Relative Optimization for a Large Ranking Model
• IntSR: An Integrated Generative Framework for Search and Recommendation
• Rejuvenating Cross-Entropy Loss in Knowledge Distillation for Recommender Systems
• Mitigating Propensity Bias of Large Language Models for Recommender Systems
• Bootstrapping User and Item Representations for One-Class Collaborative Filtering
• Identifying and Upweighting Power-Niche Users to Mitigate Popularity Bias in Recommendations
• Understanding Embedding Scaling in Collaborative Filtering
• Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation
• Hierarchical Fashion Graph Network for Personalized Outfit Recommendation
• Metapath- and Entity-aware Graph Neural Network for Recommendation
• Learning Effective Representations for Person-Job Fit by Feature Fusion
• Beyond Regularity: Modeling Chaotic Mobility Patterns for Next Location Prediction
• Towards a Real-World Aligned Benchmark for Unlearning in Recommender Systems
• Membership Inference Attacks on Recommender System: A Survey
• SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
• CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback
• Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation
• Multi-interest transfer using contrastive learning for cross-domain recommendation
• Customized Retrieval-Augmented Generation with LLM for Debiasing Recommendation Unlearning
• Conv4Rec: A 1-by-1 Convolutional AutoEncoder for User Profiling through Joint Analysis of Implicit and Explicit Feedbacks
• AutoML for Deep Recommender Systems: A Survey
• Ready for Emerging Threats to Recommender Systems? A Graph Convolution-based Generative Shilling Attack
• RecMind: LLM-Enhanced Graph Neural Networks for Personalized Consumer Recommendations
• Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing
• Unified Interaction Foundational Model (UIFM) for Predicting Complex User and System Behavior
• Contrastive Learning for Recommender System
• Hybrid Matrix Factorization Based Graph Contrastive Learning for Recommendation System
• A Node-Aware Dynamic Quantization Approach for Graph Collaborative Filtering
• Hyperbolic Neural Collaborative Recommender
• LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models
• Modeling User Preferences as Distributions for Optimal Transport-based Cross-domain Recommendation under Non-overlapping Settings
• EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation
• Cloud-Device Collaborative Agents for Sequential Recommendation
• Collaborative local–global context modeling for session-based recommendation
• Ultra Fast Warm Start Solution for Graph Recommendations
• Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMs
• Sampling-Decomposable Generative Adversarial Recommender
• MLLMRec: Exploring the Potential of Multimodal Large Language Models in Recommender Systems
• Next Point-of-interest (POI) Recommendation Model Based on Multi-modal Spatio-temporal Context Feature Embedding
• UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation
• GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection
• Federated Consistency- and Complementarity-aware Consensus-enhanced Recommendation
• A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions
• Improving Recommendation Fairness via Graph Structure and Representation Augmentation
• A Self-Supervised Mixture-of-Experts Framework for Multi-behavior Recommendation
• Retrieval-Augmented Review Generation for Poisoning Recommender Systems
• Membership Inference Attacks on LLM-based Recommender Systems
• Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
• Diverse Negative Sampling for Implicit Collaborative Filtering
• Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation
• LLM-Enhanced Linear Autoencoders for Recommendation
• MHSNet:An MoE-based Hierarchical Semantic Representation Network for Accurate Duplicate Resume Detection with Large Language Model
• Breaking the Aggregation Bottleneck in Federated Recommendation: A Personalized Model Merging Approach
• Deep Graph Neural Point Process For Learning Temporal Interactive Networks
• Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations
• When Algorithms Mirror Minds: A Confirmation-Aware Social Dynamic Model of Echo Chamber and Homogenization Traps
• Mitigating Filter Bubble from the Perspective of Community Detection: A Universal Framework
• Representation Quantization for Collaborative Filtering Augmentation
• Hypercomplex Prompt-aware Multimodal Recommendation
• Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation
• Multimodal Fusion And Sparse Attention-based Alignment Model for Long Sequential Recommendation
• LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval
• Towards Comprehensible Recommendation with Large Language Model Fine-tuning
• Multi-Sample based Contrastive Loss for Top-k Recommendation
• Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph
• SocRipple: A Two-Stage Framework for Cold-Start Video Recommendations
• RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation
• Uncertainty-Aware Semantic Decoding for LLM-Based Sequential Recommendation
• Harnessing Adaptive Topology Representations for Zero-Shot Graph Question Answering
• Graph Federated Learning for Personalized Privacy Recommendation
• Semantic Item Graph Enhancement for Multimodal Recommendation
• KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation
• Community-Aware Social Community Recommendation
• Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation
• I³-MRec: Invariant Learning with Information Bottleneck for Incomplete Modality Recommendation
• Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation
• Parameter-Efficient Single Collaborative Branch for Recommendation
• Breaking the Top-K Barrier: Advancing Top-K Ranking Metrics Optimization in Recommender Systems
• From Generation to Consumption: Personalized List Value Estimation for Re-ranking
• Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation
• End-to-End Personalization: Unifying Recommender Systems with Large Language Models
• CM³: Calibrating Multimodal Recommendation
• Are Recommenders Self-Aware? Label-Free Recommendation Performance Estimation via Model Uncertainty
• AUV-Fusion: Cross-Modal Adversarial Fusion of User Interactions and Visual Perturbations Against VARS
• VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation
• A Diffusion Model for POI Recommendation
• Beyond Interactions: Node-Level Graph Generation for Knowledge-Free Augmentation in Recommender Systems
• HIAL: A New Paradigm for Hypergraph Active Learning via Influence Maximization

Related

• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• How Powerful is Graph Convolution for Recommendation?
• UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation
• LightGCN: Evaluated and Enhanced
• Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach