Data to 7 Oct 2026

Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification

arXiv 2009.03509 ↗First posted 8 Sep 2020cs.LG stat.MLcited by 500

Not on the map. Why?

Abstract (arXiv)

Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. GNN performs feature propagation by a neural network to make predictions, while LPA uses label propagation across graph adjacency matrix to get results. However, there is still no effective way to directly combine these two kinds of algorithms. To address this issue, we propose a novel Unified Message Passaging Model (UniMP) that can incorporate feature and label propagation at both training and inference time. First, UniMP adopts a Graph Transformer network, taking feature embedding and label embedding as input information for propagation. Second, to train the network without overfitting in self-loop input label information, UniMP introduces a masked label prediction strategy, in which some percentage of input label information are masked at random, and then predicted. UniMP conceptually unifies feature propagation and label propagation and is empirically powerful. It obtains new state-of-the-art semi-supervised classification results in Open Graph Benchmark (OGB).

Key facts. Cited by 500 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 52; 2023: 86; 2024: 138; 2025: 115; 2026: 74.

500 papers.

Sort:

By area:

2021How Attentive are Graph Attention Networks?cited by 818
2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
2023Language is All a Graph Needscited by 219
2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 217
2022Structure-Aware Transformer for Graph Representation Learningcited by 191
2021Training Graph Neural Networks with 1000 Layerscited by 169
2023All in One: Multi-task Prompting for Graph Neural Networkscited by 147

38 more

2021Graph Unlearningcited by 129
2022Transformer for Graphs: An Overview from Architecture Perspectivecited by 107
2021GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddingscited by 90
2023Where Did the Gap Go? Reassessing the Long-Range Graph Benchmarkcited by 83
2022Graph Attention Multi-Layer Perceptroncited by 82
2021SE(3) Equivariant Graph Neural Networks with Complete Local Framescited by 75
2023Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modelingcited by 75
2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
2021Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Frameworkcited by 69
2023Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothingcited by 67
2022Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observationscited by 64
2023Graph Prompt Learning: A Comprehensive Survey and Beyondcited by 61
2022Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyondcited by 60
2021DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networkscited by 59
2022Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learningcited by 58
2021LOKI: Long Term and Key Intentions for Trajectory Predictioncited by 57
2023GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detectioncited by 57
2022GraphWorld: Fake Graphs Bring Real Insights for GNNscited by 56
2024GOFA: A Generative One-For-All Model for Joint Graph Language Modelingcited by 56
2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendationcited by 56
2021Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced trainingcited by 54
2023A Fractional Graph Laplacian Approach to Oversmoothingcited by 45
2025RelGNN: Composite Message Passing for Relational Deep Learningcited by 45
2024Can Graph Learning Improve Planning in LLM-based Agents?cited by 42
2025On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learningcited by 42
2021Bag of Tricks for Node Classification with Graph Neural Networkscited by 40
2021Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networkscited by 38
2024Instant Policy: In-Context Imitation Learning via Graph Diffusioncited by 38
2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
2021Neural Link Prediction with Walk Poolingcited by 36
2022Rewiring with Positional Encodings for Graph Neural Networkscited by 35
2023Cooperative Graph Neural Networkscited by 35
2022Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregationcited by 34
2023NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomicscited by 33
2024GraphEdit: Large Language Models for Graph Structure Learningcited by 33
2023A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretrainingcited by 32
2024PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learningcited by 32
2024DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassemblycited by 31

50 most cited of 500 All 500 (JSON)