mlsanityData to 14 Oct 2026

Structure-Aware DropEdge Towards Deep Graph Convolutional Networks

arXiv 2306.12091 ↗First posted 21 Jun 2023cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

It has been discovered that Graph Convolutional Networks (GCNs) encounter a remarkable drop in performance when multiple layers are piled up. The main factor that accounts for why deep GCNs fail lies in over-smoothing, which isolates the network output from the input with the increase of network depth, weakening expressivity and trainability. In this paper, we start by investigating refined measures upon DropEdge -- an existing simple yet effective technique to relieve over-smoothing. We term our method as DropEdge++ for its two structure-aware samplers in contrast to DropEdge: layer-dependent sampler and feature-dependent sampler. Regarding the layer-dependent sampler, we interestingly find that increasingly sampling edges from the bottom layer yields superior performance than the decreasing counterpart as well as DropEdge. We theoretically reveal this phenomenon with Mean-Edge-Number (MEN), a metric closely related to over-smoothing. For the feature-dependent sampler, we associate the edge sampling probability with the feature similarity of node pairs, and prove that it further correlates the convergence subspace of the output layer with the input features. Extensive experiments on several node classification benchmarks, including both full- and semi- supervised tasks, illustrate the efficacy of DropEdge++ and its compatibility with a variety of backbones by achieving generally better performance over DropEdge and the no-drop version.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 34 of its 52 references that are in the map. First posted on arXiv 21 Jun 2023.

Builds on

34 of 52 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  8. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  9. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  10. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  11. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  12. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
22 more
  1. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  2. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  3. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
  4. 2020Simple and Deep Graph Convolutional Networkscited by 860
  5. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  6. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  7. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  8. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  9. 2019Diffusion Improves Graph Learningcited by 414
  10. 2016Learning Convolutional Neural Networks for Graphscited by 314
  11. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  12. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  13. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  14. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  15. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  16. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 114
  17. 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
  18. 2020Tackling Over-Smoothing for General Graph Convolutional Networkscited by 66
  19. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  20. 2020Spectral Graph Attention Network with Fast Eigen-approximationcited by 18
  21. 2021Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classificationcited by 8
  22. 2019Quantifying the Alignment of Graph and Features in Deep Learningcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 1.

3 papers.

  1. 2024ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networkscited by 7
  2. 2024Up-sampling-only and Adaptive Mesh-based GNN for Simulating Physical Systemscited by 4
  3. 2025Simplifying Graph Convolutional Networks with Redundancy-Free Neighborscited by 0