mlsanityData to 7 Oct 2026

Learning How to Propagate Messages in Graph Neural Networks

arXiv 2310.00697 ↗First posted 1 Oct 2023cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

This paper studies the problem of learning message propagation strategies for graph neural networks (GNNs). One of the challenges for graph neural networks is that of defining the propagation strategy. For instance, the choices of propagation steps are often specialized to a single graph and are not personalized to different nodes. To compensate for this, in this paper, we present learning to propagate, a general learning framework that not only learns the GNN parameters for prediction but more importantly, can explicitly learn the interpretable and personalized propagate strategies for different nodes and various types of graphs. We introduce the optimal propagation steps as latent variables to help find the maximum-likelihood estimation of the GNN parameters in a variational Expectation-Maximization (VEM) framework. Extensive experiments on various types of graph benchmarks demonstrate that our proposed framework can significantly achieve better performance compared with the state-of-the-art methods, and can effectively learn personalized and interpretable propagate strategies of messages in GNNs.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 41 of its 57 references that are in the map. First posted on arXiv 1 Oct 2023.

Builds on

41 of 57 references.

References · 41

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2016Variational Inference: A Review for Statisticianscited by 1,466
  11. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  12. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
29 more
  1. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  2. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  3. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  4. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  5. 2020Simple and Deep Graph Convolutional Networkscited by 857
  6. 2015Automatic differentiation in machine learning: a surveycited by 846
  7. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  8. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  9. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  10. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  11. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  12. 2018Bilevel Programming for Hyperparameter Optimization and Meta-Learningcited by 403
  13. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  14. 2015Gradient-based Hyperparameter Optimization through Reversible Learningcited by 357
  15. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  16. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  17. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  18. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  19. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  20. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  21. 2015Variational Information Maximisation for Intrinsically Motivated Reinforcement Learningcited by 142
  22. 2017Online Learning Rate Adaptation with Hypergradient Descentcited by 117
  23. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 113
  24. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  25. 2018On Learning Intrinsic Rewards for Policy Gradient Methodscited by 100
  26. 2019Auto-GNN: Neural Architecture Search of Graph Neural Networkscited by 73
  27. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  28. 2019GraphNAS: Graph Neural Architecture Search with Reinforcement Learningcited by 41
  29. 2020Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphscited by 38

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 12; 2025: 5; 2026: 1.

23 papers.

Sort:

By area:

  1. 2024AnyGraph: Graph Foundation Model in the Wildcited by 51
  2. 2024Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignmentcited by 50
  3. 2023Prompt-based Distribution Alignment for Unsupervised Domain Adaptationcited by 44
  4. 2023Simple and Asymmetric Graph Contrastive Learning without Augmentationscited by 37
  5. 2024Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Modelscited by 24
  6. 2024How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspectivecited by 14
  7. 2024Federated Graph Learning for Cross-Domain Recommendationcited by 9
  8. 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generationcited by 8
  9. 2024LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generationcited by 8
  10. 2024MolBind: Multimodal Alignment of Language, Molecules, and Proteinscited by 7
  11. 2025Subgraph Federated Learning for Local Generalizationcited by 6
  12. 2023Certifiably Robust Graph Contrastive Learningcited by 5
11 more
  1. 2024Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networkscited by 4
  2. 2024Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modelingcited by 4
  3. 2024Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedbackcited by 2
  4. 2024GeomCLIP: Contrastive Geometry-Text Pre-training for Moleculescited by 2
  5. 2025Early-Exit Graph Neural Networkscited by 2
  6. 2023Prioritized Propagation in Graph Neural Networkscited by 1
  7. 2023Learning to Reweight for Graph Neural Networkcited by 1
  8. 2025A Decision-Based Heterogenous Graph Attention Network for Multi-Class Fake News Detectioncited by 1
  9. 2025CONTINUUM: Detecting APT Attacks through Spatial-Temporal Graph Neural Networkscited by 0
  10. 2025Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learningcited by 0
  11. 2026Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learningcited by 0