Classic
Cora
Structure
1Graphs
2,708Nodes
5,429Edges
7Classes
1433Node Feature Dim
0.8252Homophily
Coverage
1233Results
1Variants
198Papers
- ICML 2026: RADE: Random Add-Drop Edge as a Regularizer RADE: Random Add-Drop Edge as a Regularizer ICML 2026
- Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
- From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning
- Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding
- Adaptive Negative Scheduling for Graph Contrastive Learning Adaptive Negative Scheduling for Graph Contrastive Learning
- Latent-Hysteresis Graph ODEs: Modeling Coupled Topology-Feature Evolution via Continuous Phase Transitions Latent-Hysteresis Graph ODEs: Modeling Coupled Topology-Feature Evolution via Continuous Phase Transitions
- ICLR 2026: Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors ICLR 2026
- Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow
- TMLR 2026: Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks TMLR 2026
- Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
- KDD 2026: Generalizing GNNs with Tokenized Mixture of Experts Generalizing GNNs with Tokenized Mixture of Experts KDD 2026
- Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms
- Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach
- SPGCL: Simple yet Powerful Graph Contrastive Learning via SVD-Guided Structural Perturbation SPGCL: Simple yet Powerful Graph Contrastive Learning via SVD-Guided Structural Perturbation
- GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition
- Position: Don't be Afraid of Over-Smoothing And Over-Squashing Position: Don't be Afraid of Over-Smoothing And Over-Squashing
- CORE: Contrastive Masked Feature Reconstruction on Graphs CORE: Contrastive Masked Feature Reconstruction on Graphs
- Rethinking Semi-Supervised Node Classification with Self-Supervised Graph Clustering Rethinking Semi-Supervised Node Classification with Self-Supervised Graph Clustering
- Gauge-Equivariant Graph Networks via Self-Interference Cancellation Gauge-Equivariant Graph Networks via Self-Interference Cancellation
- NeurIPS 2025: Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction NeurIPS 2025
- NeurIPS 2025: One Prompt Fits All: Universal Graph Adaptation for Pretrained Models One Prompt Fits All: Universal Graph Adaptation for Pretrained Models NeurIPS 2025
- Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
- Exact Verification of Graph Neural Networks with Incremental Constraint Solving Exact Verification of Graph Neural Networks with Incremental Constraint Solving
- KDD 2025: Discrepancy-Aware Graph Mask Auto-Encoder Discrepancy-Aware Graph Mask Auto-Encoder KDD 2025
- Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
- TMLR 2025: Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment TMLR 2025
- ICLR 2025: Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing ICLR 2025
- KDD 2025: Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarsening Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarsening KDD 2025
- Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models
- IJCAI 2025: Rethinking Graph Contrastive Learning through Relative Similarity Preservation Rethinking Graph Contrastive Learning through Relative Similarity Preservation IJCAI 2025
- TMLR 2025: Towards Efficient Training of Graph Neural Networks: A Multiscale Approach Towards Efficient Training of Graph Neural Networks: A Multiscale Approach TMLR 2025
- TMLR 2025: Diffusion on Graph: Augmentation of Graph Structure for Node Classification Diffusion on Graph: Augmentation of Graph Structure for Node Classification TMLR 2025
- LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models
- KDD 2025: GCoT: Chain-of-Thought Prompt Learning for Graphs GCoT: Chain-of-Thought Prompt Learning for Graphs KDD 2025
- JMLR 2025: Enhancing Graph Representation Learning with Localized Topological Features Enhancing Graph Representation Learning with Localized Topological Features JMLR 2025
- Revisiting the Necessity of Graph Learning and Common Graph Benchmarks Revisiting the Necessity of Graph Learning and Common Graph Benchmarks
- NeurIPS 2024: Graph Neural Networks Need Cluster-Normalize-Activate Modules Graph Neural Networks Need Cluster-Normalize-Activate Modules NeurIPS 2024
- GaGSL: Global-augmented Graph Structure Learning via Graph Information Bottleneck GaGSL: Global-augmented Graph Structure Learning via Graph Information Bottleneck
- ICLR 2024: When Graph Neural Networks Meet Dynamic Mode Decomposition When Graph Neural Networks Meet Dynamic Mode Decomposition ICLR 2024
- TMLR 2024: SCNode: Spatial and Contextual Coordinates for Graph Representation Learning SCNode: Spatial and Contextual Coordinates for Graph Representation Learning TMLR 2024
- Negative-Free Self-Supervised Gaussian Embedding of Graphs Negative-Free Self-Supervised Gaussian Embedding of Graphs
- JMLR 2024: Transformers from Diffusion: A Unified Framework for Neural Message Passing Transformers from Diffusion: A Unified Framework for Neural Message Passing JMLR 2024
- Disentangled Generative Graph Representation Learning Disentangled Generative Graph Representation Learning
- Graph Triple Attention Network: A Decoupled Perspective Graph Triple Attention Network: A Decoupled Perspective
- KDD 2024: TSC: A Simple Two-Sided Constraint against Over-Smoothing TSC: A Simple Two-Sided Constraint against Over-Smoothing KDD 2024
- LoG 2024: xAI-Drop: Don't Use What You Cannot Explain xAI-Drop: Don't Use What You Cannot Explain LoG 2024
- All Against Some: Efficient Integration of Large Language Models for Message Passing in Graph Neural Networks All Against Some: Efficient Integration of Large Language Models for Message Passing in Graph Neural Networks
- ICLR 2024: The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited ICLR 2024
- TinyGraph: Joint Feature and Node Condensation for Graph Neural Networks TinyGraph: Joint Feature and Node Condensation for Graph Neural Networks
- TMLR 2024: Graph Pooling via Ricci Flow Graph Pooling via Ricci Flow TMLR 2024
- Graph Neural Reaction Diffusion Models Submitted to the editors June 2023. Accepted in March 2024. Graph Neural Reaction Diffusion Models Submitted to the editors June 2023. Accepted in March 2024.
- NeurIPS 2024: Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights NeurIPS 2024
- NeurIPS 2024: ProG: A Graph Prompt Learning Benchmark ProG: A Graph Prompt Learning Benchmark NeurIPS 2024
- NeurIPS 2024: Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models NeurIPS 2024
- ICLR 2024: Fully-inductive Node Classification on Arbitrary Graphs Fully-inductive Node Classification on Arbitrary Graphs ICLR 2024
- Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models
- ICLR 2024: Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning ICLR 2024
- ICML 2024: Rethinking Independent Cross-Entropy Loss For Graph-Structured Data Rethinking Independent Cross-Entropy Loss For Graph-Structured Data ICML 2024
- NeurIPS 2024: HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning NeurIPS 2024
- LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework
- E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification
- WWW 2024: Polynomial Selection in Spectral Graph Neural Networks: An Error-Sum of Function Slices Approach Polynomial Selection in Spectral Graph Neural Networks: An Error-Sum of Function Slices Approach WWW 2024
- Graph Neural Aggregation-diffusion with Metastability Graph Neural Aggregation-diffusion with Metastability
- Simple Graph Condensation Simple Graph Condensation
- Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
- Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework. Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework.
- AAAI 2024: Large Language Model Meets Graph Neural Network in Knowledge Distillation Large Language Model Meets Graph Neural Network in Knowledge Distillation AAAI 2024
- ICML 2024: Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching ICML 2024
- Two Trades are not Baffled: Condensing Graph via Crafting Rational Gradient Matching Two Trades are not Baffled: Condensing Graph via Crafting Rational Gradient Matching
- WWW 2024: EXGC: Bridging Efficiency and Explainability in Graph Condensation EXGC: Bridging Efficiency and Explainability in Graph Condensation WWW 2024
- IJCAI 2024: Efficient Tuning and Inference for Large Language Models on Textual Graphs Efficient Tuning and Inference for Large Language Models on Textual Graphs IJCAI 2024
- Design your own universe: a physics-informed agnostic method for enhancing graph neural networks Design your own universe: a physics-informed agnostic method for enhancing graph neural networks
- ICML 2024: Understanding Heterophily for Graph Neural Networks Understanding Heterophily for Graph Neural Networks ICML 2024
- DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing
- LoG 2023: Propagate & Distill: Towards Effective Graph Learners Using Propagation-Embracing MLPs Propagate & Distill: Towards Effective Graph Learners Using Propagation-Embracing MLPs LoG 2023
- ICLR 2023: Effective Structural Encodings via Local Curvature Profiles Effective Structural Encodings via Local Curvature Profiles ICLR 2023
- Graph Agent: Explicit Reasoning Agent for Graphs Graph Agent: Explicit Reasoning Agent for Graphs
- KDD 2023: Marginal Nodes Matter: Towards Structure Fairness in Graphs Marginal Nodes Matter: Towards Structure Fairness in Graphs KDD 2023
- Spectral-Aware Augmentation for Enhanced Graph Representation Learning Spectral-Aware Augmentation for Enhanced Graph Representation Learning
- WWW 2023: Fast Graph Condensation with Structure-based Neural Tangent Kernel Fast Graph Condensation with Structure-based Neural Tangent Kernel WWW 2023
- GraphText: Graph Reasoning in Text Space GraphText: Graph Reasoning in Text Space
- Operator Learning Meets Numerical Analysis: Improving Neural Networks through Iterative Methods Operator Learning Meets Numerical Analysis: Improving Neural Networks through Iterative Methods
- TMLR 2023: On the Equivalence of Graph Convolution and Mixup On the Equivalence of Graph Convolution and Mixup TMLR 2023
- Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning
- UGSL: A Unified Framework for Benchmarking Graph Structure Learning UGSL: A Unified Framework for Benchmarking Graph Structure Learning
- The Expressive Power of Graph Neural Networks: A Survey The Expressive Power of Graph Neural Networks: A Survey
- Language is All a Graph Needs Language is All a Graph Needs
- ICLR 2023: VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs ICLR 2023
- AAAI 2023: Feature Transportation Improves Graph Neural Networks Feature Transportation Improves Graph Neural Networks AAAI 2023
- How Curvature Enhance the Adaptation Power of Framelet GCNs How Curvature Enhance the Adaptation Power of Framelet GCNs
- Frameless Graph Knowledge Distillation Frameless Graph Knowledge Distillation
- ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning
- Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation
- ICML 2023: Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication ICML 2023
- KDD 2023: HomoGCL: Rethinking Homophily in Graph Contrastive Learning HomoGCL: Rethinking Homophily in Graph Contrastive Learning KDD 2023
- Oversmoothing: A Nightmare for Graph Contrastive Learning? Oversmoothing: A Nightmare for Graph Contrastive Learning?
- AAAI 2023: Union Subgraph Neural Networks Union Subgraph Neural Networks AAAI 2023
- IJCAI 2023: Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention IJCAI 2023
- ICML 2023: Feature Expansion for Graph Neural Networks Feature Expansion for Graph Neural Networks ICML 2023
- IJCAI 2023: Hierarchical Transformer for Scalable Graph Learning Hierarchical Transformer for Scalable Graph Learning IJCAI 2023
- ICML 2023: Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks ICML 2023
- Framelet Message Passing Framelet Message Passing
- Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional Networks Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional Networks
- ICLR 2023: Discovering Data Geometry: Energy-Driven Neural Diffusion Discovering Data Geometry: Energy-Driven Neural Diffusion ICLR 2023
- ICML 2022: TIDE: Time Derivative Diffusion for Deep Learning on Graphs TIDE: Time Derivative Diffusion for Deep Learning on Graphs ICML 2022
- LoG 2022: You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets LoG 2022
- AAAI 2022: Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating AAAI 2022
- From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm
- Comprehensive Analysis of Over-smoothing in Graph Neural Networks from Markov Chains Perspective Comprehensive Analysis of Over-smoothing in Graph Neural Networks from Markov Chains Perspective
- Graph Contrastive Learning with Implicit Augmentations Graph Contrastive Learning with Implicit Augmentations
- TMLR 2022: Causally-guided Regularization of Graph Attention Improves Generalizability Causally-guided Regularization of Graph Attention Improves Generalizability TMLR 2022
- Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learning Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learning
- NeurIPS 2022: Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again NeurIPS 2022
- NeurIPS 2022: Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative NeurIPS 2022
- GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials
- NeurIPS 2022: NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs NeurIPS 2022
- ICML 2022: Structural Entropy Guided Graph Hierarchical Pooling Structural Entropy Guided Graph Hierarchical Pooling ICML 2022
- NeurIPS 2022: NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search NeurIPS 2022
- KDD 2022: Condensing Graphs via One-Step Gradient Matching Condensing Graphs via One-Step Gradient Matching KDD 2022
- Decoupled Self-supervised Learning for Non-Homophilou Graphs Decoupled Self-supervised Learning for Non-Homophilou Graphs
- Mixed Graph Contrastive Network for Semi-Supervised Node Classification Mixed Graph Contrastive Network for Semi-Supervised Node Classification
- Discovering the Representation Bottleneck of Graph Neural Networks Discovering the Representation Bottleneck of Graph Neural Networks
- Reinforcement learning on graphs: A survey Reinforcement learning on graphs: A survey
- Augmentation-Free Graph Contrastive Learning with Performance Guarantee Augmentation-Free Graph Contrastive Learning with Performance Guarantee
- NeurIPS 2022: Metropolis-Hastings Data Augmentation for Graph Neural Networks Metropolis-Hastings Data Augmentation for Graph Neural Networks NeurIPS 2022
- Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization
- Neighbor Enhanced Graph Convolutional Networks for Node Classification and Recommendation Neighbor Enhanced Graph Convolutional Networks for Node Classification and Recommendation
- ICLR 2022: Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks ICLR 2022
- Graph Masked Autoencoders with Transformers Graph Masked Autoencoders with Transformers
- ICML 2022: Graph-Coupled Oscillator Networks Graph-Coupled Oscillator Networks ICML 2022
- TMLR 2022: Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings TMLR 2022
- NeurIPS 2022: Contrastive Laplacian Eigenmaps Contrastive Laplacian Eigenmaps NeurIPS 2022
- Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions
- AAAI 2021: Block Modeling-Guided Graph Convolutional Neural Networks Block Modeling-Guided Graph Convolutional Neural Networks AAAI 2021
- Simplifying approach to Node Classification in Graph Neural Networks Simplifying approach to Node Classification in Graph Neural Networks
- NeurIPS 2021: Node Dependent Local Smoothing for Scalable Graph Learning Node Dependent Local Smoothing for Scalable Graph Learning NeurIPS 2021
- ICLR 2021: Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation ICLR 2021
- AAAI 2021: Orthogonal Graph Neural Networks Orthogonal Graph Neural Networks AAAI 2021
- Towards Self-Explainable Graph Neural Network Towards Self-Explainable Graph Neural Network
- IJCAI 2021: Understanding Structural Vulnerability in Graph Convolutional Networks Understanding Structural Vulnerability in Graph Convolutional Networks IJCAI 2021
- KDD 2021: ROD: Reception-aware Online Distillation for Sparse Graphs ROD: Reception-aware Online Distillation for Sparse Graphs KDD 2021
- ICML 2021: GRAND: Graph Neural Diffusion GRAND: Graph Neural Diffusion ICML 2021
- Graph-MLP: Node Classification without Message Passing in Graph Graph-MLP: Node Classification without Message Passing in Graph
- Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping
- GraphTheta: A Distributed Graph Neural Network Learning System With Flexible Training Strategy GraphTheta: A Distributed Graph Neural Network Learning System With Flexible Training Strategy
- ICLR 2021: AutoGL: A Library for Automated Graph Learning AutoGL: A Library for Automated Graph Learning ICLR 2021
- WWW 2021: SelfGNN: Self-supervised Graph Neural Networks without explicit negative sampling SelfGNN: Self-supervised Graph Neural Networks without explicit negative sampling WWW 2021
- Graph Unlearning Graph Unlearning
- Bag of Tricks for Node Classification with Graph Neural Networks Bag of Tricks for Node Classification with Graph Neural Networks
- Adversarial Graph Disentanglement with Component-specific Aggregation Adversarial Graph Disentanglement with Component-specific Aggregation
- ICML 2021: Graph Neural Networks Inspired by Classical Iterative Algorithms Graph Neural Networks Inspired by Classical Iterative Algorithms ICML 2021
- WWW 2021: Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework WWW 2021
- ICML 2021: How Framelets Enhance Graph Neural Networks How Framelets Enhance Graph Neural Networks ICML 2021
- NeurIPS 2021: Learning Conjoint Attentions for Graph Neural Nets Learning Conjoint Attentions for Graph Neural Nets NeurIPS 2021
- IJCAI 2020: Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification IJCAI 2020
- Learning to Drop: Robust Graph Neural Network via Topological Denoising Learning to Drop: Robust Graph Neural Network via Topological Denoising
- NeurIPS 2020: Scalable Graph Neural Networks via Bidirectional Propagation Scalable Graph Neural Networks via Bidirectional Propagation NeurIPS 2020
- Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
- Bi-GCN: Binary Graph Convolutional Network Bi-GCN: Binary Graph Convolutional Network
- IJCAI 2020: Multi-hop Attention Graph Neural Networks Multi-hop Attention Graph Neural Networks IJCAI 2020
- Learned Low Precision Graph Neural Networks Learned Low Precision Graph Neural Networks
- AAAI 2020: Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning AAAI 2020
- AAAI 2020: Rethinking Graph Regularization for Graph Neural Networks Rethinking Graph Regularization for Graph Neural Networks AAAI 2020
- AAAI 2020: SAIL: Self-Augmented Graph Contrastive Learning SAIL: Self-Augmented Graph Contrastive Learning AAAI 2020
- Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
- Tackling Over-Smoothing for General Graph Convolutional Networks Tackling Over-Smoothing for General Graph Convolutional Networks
- Self-supervised Learning on Graphs: Deep Insights and New Directions Self-supervised Learning on Graphs: Deep Insights and New Directions
- Understanding and Resolving Performance Degradation in Deep Graph Convolutional Networks Understanding and Resolving Performance Degradation in Deep Graph Convolutional Networks
- NeurIPS 2020: Towards Deeper Graph Neural Networks with Differentiable Group Normalization Towards Deeper Graph Neural Networks with Differentiable Group Normalization NeurIPS 2020
- The Impact of Global Structural Information in Graph Neural Networks Applications The Impact of Global Structural Information in Graph Neural Networks Applications
- Non-Local Graph Neural Networks Non-Local Graph Neural Networks
- Revisiting Oversmoothing in Deep GCNs Revisiting Oversmoothing in Deep GCNs
- NeurIPS 2020: Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks NeurIPS 2020
- Spectral Graph Attention Network with Fast Eigen-approximation Spectral Graph Attention Network with Fast Eigen-approximation
- Neural Message Passing on High Order Paths Neural Message Passing on High Order Paths
- Graph-Bert: Only Attention is Needed for Learning Graph Representations Graph-Bert: Only Attention is Needed for Learning Graph Representations
- ICML 2019: Continuous Graph Neural Networks Continuous Graph Neural Networks ICML 2019
- AAAI 2019: Graph Neural Ordinary Differential Equations Graph Neural Ordinary Differential Equations AAAI 2019
- ICLR 2019: GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding ICLR 2019
- GraphMix: Improved Training of GNNs for Semi-Supervised Learning GraphMix: Improved Training of GNNs for Semi-Supervised Learning
- Multi-Scale Attributed Node Embedding Multi-Scale Attributed Node Embedding
- Auto-GNN: Neural Architecture Search of Graph Neural Networks Auto-GNN: Neural Architecture Search of Graph Neural Networks
- Graph Representation Learning: A Survey Graph Representation Learning: A Survey
- IJCAI 2019: SPAGAN: Shortest Path Graph Attention Network SPAGAN: Shortest Path Graph Attention Network IJCAI 2019
- Fast Haar Transforms for Graph Neural Networks Fast Haar Transforms for Graph Neural Networks
- Pre-Training Graph Neural Networks for Generic Structural Feature Extraction Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
- AAAI 2019: Power up! Robust Graph Convolutional Network via Graph Powering Power up! Robust Graph Convolutional Network via Graph Powering AAAI 2019
- Graph U-Nets Graph U-Nets
- ICML 2019: Learning Discrete Structures for Graph Neural Networks Learning Discrete Structures for Graph Neural Networks ICML 2019
- A Comprehensive Survey on Graph Neural Networks A Comprehensive Survey on Graph Neural Networks
- Deep Learning on Graphs: A Survey Deep Learning on Graphs: A Survey
- AAAI 2018: Hypergraph Neural Networks Hypergraph Neural Networks AAAI 2018
- MotifNet: a motif-based Graph Convolutional Network for directed graphs MotifNet: a motif-based Graph Convolutional Network for directed graphs
- SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
- ICLR 2017: Graph Attention Networks Graph Attention Networks ICLR 2017
- Topology Adaptive Graph Convolutional Networks Topology Adaptive Graph Convolutional Networks
- Geometric deep learning on graphs and manifolds using mixture model CNNs Geometric deep learning on graphs and manifolds using mixture model CNNs
- ICML 2016: Revisiting Semi-Supervised Learning with Graph Embeddings Revisiting Semi-Supervised Learning with Graph Embeddings ICML 2016
Node classification Predict one of seven research-topic labels for every paper in a single citation network. Evaluated by Accuracy.
Dataset details
Task
Predict one of seven research-topic labels for every paper in a single citation network. The standard Planetoid formulation is transductive, so the features and graph position of validation and test nodes are available during training while their labels are withheld.
Data
The commonly used Planetoid version contains 2,708 machine-learning papers connected by citation links. It is a processed subset of the larger Cora research-paper collection; other datasets called Cora, including citation-matching corpora and Cora-ML, are not interchangeable with it.
Features
Each paper has a sparse 1,433-dimensional binary bag-of-words vector indicating selected vocabulary terms. PyG exposes 10,556 directed edge entries after processing the citation relations and reports seven classes.
Splits and evaluation
The fixed public Planetoid split uses 20 labeled training nodes per class, 500 validation nodes, and 1,000 test nodes. Other common protocols include full-label, random, Geom-GCN, and cross-validation splits; their accuracy values should not be pooled with the public split.
Quirks and pitfalls
Cora is small, highly reused, and sensitive to the exact preprocessing and split. Published work sometimes reports results for Cora-ML or a random split simply as Cora. The OGB benchmark paper also reports feature-label leakage and duplicate-node concerns in this processed dataset, reinforcing the need to state the loader and split precisely rather than treating all Cora results as comparable.
Sources
Yang et al. 2016 fixed 20-per-class train split.
SOTA Progression
new SOTA
matches SOTA at that time
other proposed result
other baseline result
Leaderboard
| # | Model | Accuracy ↑ | AUC | Accuracy (micro F1 per L1108) | F1 | F1-macro | F1-micro | Loss | NMI | Paper |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | GraphSAGE+CNA | 0.9418
±
0.0033 | — | — | — | — | — | — | — | |
| 2 | GCN+CNA | 0.9366
±
0.0048 | — | — | — | — | — | — | — | |
| 3 | TransformerConv | 0.9350
±
0.0058 | — | — | — | — | — | — | — | |
| 4 | GAT + CNA | 0.9294
±
0.0071 | — | — | — | — | — | — | — | |
| 5 | PromptGFM | 0.9242 | — | — | — | — | — | — | — | |
| 6 | Policy-GNN | 0.9190
±
0.0140 | — | — | — | — | — | — | — | |
| 7 | RGCN + RSE (70b) | 0.9177
±
0.0038 | — | — | — | — | — | — | — | |
| 8 | GraphSAGE_(Llama3) | 0.9170
±
0.0051 | — | — | — | — | — | — | — | |
| 9 | GAT_(Llama3) | 0.9151
±
0.0035 | — | — | — | — | — | — | — | |
| 10 | LinguGraph-Llama3 (8B) | 0.9151
±
0.0046 | — | — | — | — | — | — | — | |
| 11 | ENGINE | 0.9148
±
0.0032 | — | — | — | — | — | — | — | |
| 12 | SeHGNN + RSE (8b) | 0.9138
±
0.0050 | — | — | — | — | — | — | — | |
| 13 | GIN_(Llama3) | 0.9133
±
0.0028 | — | — | — | — | — | — | — | |
| 14 | TAPE | 0.9119
±
0.0012 | — | — | — | — | — | — | — | |
| 15 | Flan-T5-base | 0.9077
±
0.0052 | — | — | — | — | — | — | — | |
| 16 | GCN_(Llama3) | 0.9077
±
0.0028 | — | — | — | — | — | — | — | |
| 17 | InstructGLM | 0.9077 | — | — | — | — | — | — | — | |
| 18 | GA | 0.9065 | — | — | — | — | — | — | — | |
| 19 | HAN + RSE (70b) | 0.9031
±
0.0038 | — | — | — | — | — | — | — | |
| 20 | GCN | 0.9004 | — | — | — | — | — | — | — | |
| 21 | RDGNN-I | 0.8991
±
0.0110 | — | — | — | — | — | — | — | |
| 22 | PDNAS-4 | 0.8980
±
0.0030 | — | — | — | — | — | — | — | |
| 23 | LPGNAS | 0.8980
±
0.0000 | — | — | — | — | — | — | — | |
| 24 | ACM-GCN | 0.8975 | — | — | — | — | — | — | — | |
| 25 | GAGA | 0.8967
±
0.0012 | — | — | — | — | — | — | — | |
| 26 | Snowball-V3 | 0.8959
±
0.0158 | — | — | — | — | — | — | — | |
| 27 | ACM-Snowball-3 | 0.8959 | — | — | — | — | — | — | — | |
| 28 | RDGNN-S | 0.8953
±
0.0122 | — | — | — | — | — | — | — | |
| 29 | UniMP + RSE (70b) | 0.8952
±
0.0041 | — | — | — | — | — | — | — | |
| 30 | SplineCNN | 0.8948
±
0.0031 | — | — | — | — | — | — | — | |
| 31 | ADR-GNN_S | 0.8943 | — | — | — | — | — | — | — | |
| 32 | PDNAS-2 | 0.8930
±
0.0010 | — | — | — | — | — | — | — | |
| 33 | PDNAS-3 | 0.8930
±
0.0010 | — | — | — | — | — | — | — | |
| 34 | TAPE | 0.8930 | — | — | — | — | — | — | — | |
| 35 | LGTL | 0.8930
±
0.0009 | — | — | — | — | — | — | — | |
| 36 | CPF | 0.8928
±
0.0070 | — | — | — | — | — | — | — | |
| 37 | LLAGA-HO | 0.8922
±
0.0010 | — | — | — | — | — | — | — | |
| 38 | TFGNN | 0.8921
±
0.0040 | — | — | — | — | — | — | — | |
| 39 | RevGAT | 0.8911
±
0.0000 | — | — | — | — | — | — | — | |
| 40 | SAGE | 0.8911
±
0.0012 | — | — | — | — | — | — | — | |
| 41 | APPNP+DropEdge | 0.8910 | — | — | — | — | — | — | — | |
| 42 | C&S | 0.8905 | — | — | — | — | — | — | — | |
| 43 | DropEdge | 0.8900 | — | — | — | — | — | — | — | |
| 44 | Flan-T5-large | 0.8893
±
0.0106 | — | — | — | — | — | — | — | |
| 45 | TADropEdge-IncepGCN | 0.8890 | — | — | — | — | — | — | — | |
| 46 | GAT | 0.8890
±
0.0000 | — | — | — | — | — | — | — | |
| 47 | GCN (LCP) | 0.8890
±
0.0100 | — | — | — | — | — | — | — | |
| 48 | LLAGA-ND | 0.8886
±
0.0013 | — | — | — | — | — | — | — | |
| 49 | FAGCN | 0.8885
±
0.0136 | — | — | — | — | — | — | — | |
| 50 | Ortho-GCNII | 0.8881 | — | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time