mlsanityData to 7 Oct 2026

DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks

arXiv 2409.19620 ↗First posted 29 Sep 2024cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

The paper discusses signed graphs, which model friendly or antagonistic relationships using edges marked with positive or negative signs, focusing on the task of link sign prediction. While Signed Graph Neural Networks (SGNNs) have advanced, they face challenges like graph sparsity and unbalanced triangles. The authors propose using data augmentation (DA) techniques to address these issues, although many existing methods are not suitable for signed graphs due to a lack of side information. They highlight that the random DropEdge method, a rare DA approach applicable to signed graphs, does not enhance link sign prediction performance. In response, they introduce the Signed Graph Augmentation (SGA) framework, which includes a structure augmentation module to identify candidate edges and a strategy for selecting beneficial candidates, ultimately improving SGNN training. Experimental results show that SGA significantly boosts the performance of SGNN models, with a notable 32.3% improvement in F1-micro for SGCN on the Slashdot dataset.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 48 of its 72 references that are in the map. First posted on arXiv 29 Sep 2024.

Builds on

48 of 72 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  9. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  10. 2018Deep Graph Infomaxcited by 1,101
  11. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  12. 2020Deep Graph Contrastive Representation Learningcited by 535
36 more
  1. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  2. 2019Diffusion Improves Graph Learningcited by 414
  3. 2021Graph Contrastive Learning Automatedcited by 287
  4. 2020Data Augmentation for Graph Neural Networkscited by 200
  5. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  6. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  7. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  8. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  9. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  10. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  11. 2018Community Interaction and Conflict on the Webcited by 72
  12. 2019Signed Graph Attention Networkscited by 62
  13. 2019Generalized Data Augmentation for Low-Resource Translationcited by 53
  14. 2020Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentationcited by 53
  15. 2021Local Augmentation for Graph Neural Networkscited by 52
  16. 2019Data Augmentation via Dependency Tree Morphing for Low-Resource Languagescited by 45
  17. 2021SDGNN: Learning Node Representation for Signed Directed Networkscited by 44
  18. 2022Spectral Augmentation for Self-Supervised Learning on Graphscited by 38
  19. 2020GraphCrop: Subgraph Cropping for Graph Classificationcited by 31
  20. 2022Metropolis-Hastings Data Augmentation for Graph Neural Networkscited by 30
  21. 2014Exploiting Social Network Structure for Person-to-Person Sentiment Analysiscited by 26
  22. 2015A Survey of Signed Network Mining in Social Mediacited by 25
  23. 2022CLNode: Curriculum Learning for Node Classificationcited by 24
  24. 2017SNE: Signed Network Embeddingcited by 20
  25. 2019Discovering Polarized Communities in Signed Networkscited by 20
  26. 2021Graph Sanitation with Application to Node Classificationcited by 20
  27. 2021SSSNET: Semi-Supervised Signed Network Clusteringcited by 20
  28. 2017SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Predictioncited by 19
  29. 2021Signed Bipartite Graph Neural Networkscited by 18
  30. 2023Graph Mixup with Soft Alignmentscited by 15
  31. 2020Signed Graph Diffusion Networkcited by 13
  32. 2019Spectral Clustering of Signed Graphs via Matrix Power Meanscited by 10
  33. 2024Self-Explainable Graph Transformer for Link Sign Predictioncited by 8
  34. 2015Measuring Partial Balance in Signed Networkscited by 4
  35. 2024Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classificationcited by 2
  36. 2024Mitigating Degree Bias in Signed Graph Neural Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024CSGDN: Contrastive Signed Graph Diffusion Network for Predicting Crop Gene-phenotype Associationscited by 2
  2. 2025THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentationcited by 0
  3. 2026Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modelingcited by 0