mlsanityData to 7 Oct 2026

Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs

arXiv 2407.14765 ↗First posted 20 Jul 2024cs.LG cs.AI cs.DBcited by 1

Not on the map. Why?

Abstract (arXiv)

Graphs are crucial for representing interrelated data and aiding predictive modeling by capturing complex relationships. Achieving high-quality graph representation is important for identifying linked patterns, leading to improvements in Graph Neural Networks (GNNs) to better capture data structures. However, challenges such as data scarcity, high collection costs, and ethical concerns limit progress. As a result, generative models and data augmentation have become more and more popular. This study explores using generated graphs for data augmentation, comparing the performance of combining generated graphs with real graphs, and examining the effect of different quantities of generated graphs on graph classification tasks. The experiments show that balancing scalability and quality requires different generators based on graph size. Our results introduce a new approach to graph data augmentation, ensuring consistent labels and enhancing classification performance.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 20 references that are in the map. First posted on arXiv 20 Jul 2024.

Builds on

15 of 20 references.

References · 15

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  5. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 231
  6. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 128
  7. 2023Leaving Reality to Imagination: Robust Classification via Generated Datasetscited by 91
  8. 2019This dataset does not exist: training models from generated imagescited by 65
  9. 2021MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graphcited by 65
  10. 2019Edge Contraction Pooling for Graph Neural Networkscited by 53
  11. 2022Spectral Augmentation for Self-Supervised Learning on Graphscited by 38
  12. 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
3 more
  1. 2019Deep Representation Learning for Social Network Analysiscited by 35
  2. 2021Data Augmentation for Graph Convolutional Network on Semi-Supervised Classificationcited by 7
  3. 2023GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generatorscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026GraphK: Variable-Size Graph Generation with Efficient Edge Constructioncited by 0