mlsanityData to 7 Oct 2026

Rethinking Graph Neural Architecture Search from Message-passing

arXiv 2103.14282 ↗First posted 26 Mar 2021cs.LG cs.AIcited by 26

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) emerged recently as a standard toolkit for learning from data on graphs. Current GNN designing works depend on immense human expertise to explore different message-passing mechanisms, and require manual enumeration to determine the proper message-passing depth. Inspired by the strong searching capability of neural architecture search (NAS) in CNN, this paper proposes Graph Neural Architecture Search (GNAS) with novel-designed search space. The GNAS can automatically learn better architecture with the optimal depth of message passing on the graph. Specifically, we design Graph Neural Architecture Paradigm (GAP) with tree-topology computation procedure and two types of fine-grained atomic operations (feature filtering and neighbor aggregation) from message-passing mechanism to construct powerful graph network search space. Feature filtering performs adaptive feature selection, and neighbor aggregation captures structural information and calculates neighbors' statistics. Experiments show that our GNAS can search for better GNNs with multiple message-passing mechanisms and optimal message-passing depth. The searched network achieves remarkable improvement over state-of-the-art manual designed and search-based GNNs on five large-scale datasets at three classical graph tasks. Codes can be found at https://github.com/phython96/GNAS-MP.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 26 Mar 2021.

Builds on

29 of 46 references.

References · 29

  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. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  7. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  9. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  10. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  11. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  12. 2020Benchmarking Graph Neural Networkscited by 672
17 more
  1. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  2. 2015Gradient-based Hyperparameter Optimization through Reversible Learningcited by 357
  3. 2017Large-Scale Evolution of Image Classifierscited by 348
  4. 2017Residual Gated Graph ConvNetscited by 341
  5. 2017Community Detection and Stochastic Block Modelscited by 317
  6. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  7. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
  8. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  9. 2017Hierarchical Representations for Efficient Architecture Searchcited by 188
  10. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 176
  11. 2019DARTS+: Improved Differentiable Architecture Search with Early Stoppingcited by 105
  12. 2019Auto-GNN: Neural Architecture Search of Graph Neural Networkscited by 73
  13. 2019SGAS: Sequential Greedy Architecture Searchcited by 69
  14. 2019Adaptive Reconstruction Network for Weakly Supervised Referring Expression Groundingcited by 37
  15. 2020Neural Architecture Search in Graph Neural Networkscited by 15
  16. 2020PV-NAS: Practical Neural Architecture Search for Video Recognitioncited by 5
  17. 2019Posterior-Guided Neural Architecture Searchcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 4; 2024: 7; 2025: 3; 2026: 1.

26 papers.

Sort:

By area:

  1. 2022On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networkscited by 63
  2. 2022PaSca: a Graph Neural Architecture Search System under the Scalable Paradigmcited by 37
  3. 2022NAS-Bench-Graph: Benchmarking Graph Neural Architecture Searchcited by 25
  4. 2022GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Featurescited by 12
  5. 2023Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platformscited by 12
  6. 2022Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directionscited by 8
  7. 2023AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networkscited by 8
  8. 2023Adversarially Robust Neural Architecture Search for Graph Neural Networkscited by 7
  9. 2022Automatic Relation-aware Graph Network Proliferationcited by 6
  10. 2024Unsupervised Graph Neural Architecture Search with Disentangled Self-supervisioncited by 5
  11. 2022Explore Contextual Information for 3D Scene Graph Generationcited by 4
  12. 2022Generalizing Aggregation Functions in GNNs:High-Capacity GNNs via Nonlinear Neighborhood Aggregatorscited by 3
14 more
  1. 2021Edge-featured Graph Neural Architecture Searchcited by 2
  2. 2024Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsificationcited by 2
  3. 2022DFG-NAS: Deep and Flexible Graph Neural Architecture Searchcited by 1
  4. 2023Graph Neural Architecture Search with GPT-4cited by 1
  5. 2024A Graph Neural Architecture Search Approach for Identifying Bots in Social Mediacited by 1
  6. 2025Behavior Importance-Aware Graph Neural Architecture Search for Cross-Domain Recommendationcited by 1
  7. 2022Efficient Automatic Machine Learning via Design Graphscited by 0
  8. 2024Causal-aware Graph Neural Architecture Search under Distribution Shiftscited by 0
  9. 2024Graph in Graph Neural Networkcited by 0
  10. 2024HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devicescited by 0
  11. 2024Spatio-Temporal Fuzzy-oriented Multi-Modal Meta-Learning for Fine-grained Emotion Recognitioncited by 0
  12. 2025How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimationcited by 0
  13. 2025GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Searchcited by 0
  14. 2026PIMPC-GNN: Physics-Informed Multi-Phase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networkscited by 0