mlsanityData to 7 Oct 2026

Edge-featured Graph Neural Architecture Search

arXiv 2109.01356 ↗First posted 3 Sep 2021cs.LG cs.AI cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have been successfully applied to learning representation on graphs in many relational tasks. Recently, researchers study neural architecture search (NAS) to reduce the dependence of human expertise and explore better GNN architectures, but they over-emphasize entity features and ignore latent relation information concealed in the edges. To solve this problem, we incorporate edge features into graph search space and propose Edge-featured Graph Neural Architecture Search to find the optimal GNN architecture. Specifically, we design rich entity and edge updating operations to learn high-order representations, which convey more generic message passing mechanisms. Moreover, the architecture topology in our search space allows to explore complex feature dependence of both entities and edges, which can be efficiently optimized by differentiable search strategy. Experiments at three graph tasks on six datasets show EGNAS can search better GNNs with higher performance than current state-of-the-art human-designed and searched-based GNNs.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 43 of its 50 references that are in the map. First posted on arXiv 3 Sep 2021.

Builds on

43 of 50 references.

References · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  7. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  8. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  9. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  10. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  11. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  12. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
31 more
  1. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  2. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  3. 2015Gated Graph Sequence Neural Networkscited by 792
  4. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  5. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  6. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  7. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  8. 2017Large-Scale Evolution of Image Classifierscited by 348
  9. 2017Residual Gated Graph ConvNetscited by 341
  10. 2017Community Detection and Stochastic Block Modelscited by 317
  11. 2018SNAS: Stochastic Neural Architecture Searchcited by 288
  12. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
  13. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  14. 2017Hierarchical Representations for Efficient Architecture Searchcited by 188
  15. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 176
  16. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  17. 2019DARTS+: Improved Differentiable Architecture Search with Early Stoppingcited by 105
  18. 2020Building powerful and equivariant graph neural networks with structural message-passingcited by 95
  19. 2020DARTS-: Robustly Stepping out of Performance Collapse Without Indicatorscited by 81
  20. 2020Factorizable Graph Convolutional Networkscited by 79
  21. 2019GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulationcited by 75
  22. 2019Auto-GNN: Neural Architecture Search of Graph Neural Networkscited by 73
  23. 2019SGAS: Sequential Greedy Architecture Searchcited by 69
  24. 2020Policy-GNN: Aggregation Optimization for Graph Neural Networkscited by 48
  25. 2018Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compressioncited by 40
  26. 2021Automated Machine Learning on Graphs: A Surveycited by 38
  27. 2021Rethinking Graph Neural Architecture Search from Message-passingcited by 26
  28. 2021Edge-Featured Graph Attention Networkcited by 18
  29. 2020Graph Neural Network Architecture Search for Molecular Property Predictioncited by 17
  30. 2020Neural Architecture Search in Graph Neural Networkscited by 15
  31. 2020On the equivalence of molecular graph convolution and molecular wave function with poor basis setcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2.

2 papers.

  1. 2022GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Featurescited by 12
  2. 2022Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directionscited by 8