mlsanityData to 14 Oct 2026

Aggregation Buffer: Revisiting DropEdge with a New Parameter Block

arXiv 2505.20840 ↗First posted 27 May 2025cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We revisit DropEdge, a data augmentation technique for GNNs which randomly removes edges to expose diverse graph structures during training. While being a promising approach to effectively reduce overfitting on specific connections in the graph, we observe that its potential performance gain in supervised learning tasks is significantly limited. To understand why, we provide a theoretical analysis showing that the limited performance of DropEdge comes from the fundamental limitation that exists in many GNN architectures. Based on this analysis, we propose Aggregation Buffer, a parameter block specifically designed to improve the robustness of GNNs by addressing the limitation of DropEdge. Our method is compatible with any GNN model, and shows consistent performance improvements on multiple datasets. Moreover, our method effectively addresses well-known problems such as degree bias or structural disparity as a unifying solution. Code and datasets are available at https://github.com/dooho00/agg-buffer.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

35 of 46 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2017Graph Attention Networkscited by 8,923
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  9. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  10. 2019Simplifying Graph Convolutional Networkscited by 1,477
  11. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  12. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
23 more
  1. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  2. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  3. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
  4. 2020Simple and Deep Graph Convolutional Networkscited by 860
  5. 2021How Attentive are Graph Attention Networks?cited by 835
  6. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  7. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  8. 2020Benchmarking Graph Neural Networkscited by 680
  9. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  10. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  11. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  12. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 152
  13. 2021From Canonical Correlation Analysis to Self-supervised Graph Neural Networkscited by 141
  14. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 85
  15. 2022What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoderscited by 82
  16. 2021Graph-based Semi-supervised Learning: A Comprehensive Reviewcited by 79
  17. 2021Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoodscited by 58
  18. 2022Token Dropping for Efficient BERT Pretrainingcited by 42
  19. 2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
  20. 2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentationcited by 31
  21. 2022DropMessage: Unifying Random Dropping for Graph Neural Networkscited by 29
  22. 2023On Generalized Degree Fairness in Graph Neural Networkscited by 28
  23. 2024Understanding Heterophily for Graph Neural Networkscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025View Space: Learning Representation across Arbitrary Graphscited by 5
  2. 2026Node4All: Learning Node Representation Beyond Datasetscited by 2
  3. 2026RADE: Random Add-Drop Edge as a Regularizercited by 0