graph-data-augmentation

List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.

A curated list of graph data augmentation papers.

Author: Tong Zhao (tzhao2@nd.edu). ICML 2022. Learning from Counterfactual Links for Link Prediction

[NeurIPS 2023] "Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift" by Yongduo Sui, Qitian Wu, Jiancan Wu, Qing Cui, Longfei Li, Jun Zhou, Xiang Wang, Xiangnan He.

Graph Data Augmentation Library for PyTorch Geometric

Re-implementation of G-Mixup: Graph Data Augmentation for Graph Classification

pip install gnn-augment — graph-augmented GNNs (GCN, GraphSAGE, GAT, GIN) for semi-supervised node classification: replace the adjacency with Katz / Rooted PageRank / Graph Gravity / LLM text-embedding views, multi-view training, sparse mode for large graphs (arXiv:1905.09087)