GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification
Li, Wen-Zhi, Wang, Chang-Dong, Xiong, Hui, Lai, Jian-Huang
–arXiv.org Artificial Intelligence
Class imbalance is the phenomenon that some classes have much fewer instances than others, which is ubiquitous in real-world graph-structured scenarios. Recent studies find that off-the-shelf Graph Neural Networks (GNNs) would under-represent minor class samples. We investigate this phenomenon and discover that the subspaces of minor classes being squeezed by those of the major ones in the latent space is the main cause of this failure. We are naturally inspired to enlarge the decision boundaries of minor classes and propose a general framework GraphSHA by Synthesizing HArder minor samples. Furthermore, to avoid the enlarged minor boundary violating the subspaces of neighbor classes, we also propose a module called SemiMixup to transmit enlarged boundary information to the interior of the minor classes while blocking information propagation from minor classes to neighbor classes. Empirically, GraphSHA shows its effectiveness in enlarging the decision boundaries of minor classes, as it outperforms various baseline methods in class-imbalanced node classification with different GNN backbone encoders over seven public benchmark datasets. Code is avilable at https://github.com/wenzhilics/GraphSHA.
arXiv.org Artificial Intelligence
Jun-16-2023
- Country:
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Asia
- China
- Guangdong Province > Guangzhou (0.04)
- Hong Kong (0.04)
- Middle East
- Israel (0.04)
- Republic of Türkiye > Istanbul Province
- Istanbul (0.04)
- Singapore (0.04)
- China
- Europe
- Austria (0.04)
- France (0.04)
- Italy > Veneto
- Venice (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Netherlands > North Holland
- Amsterdam (0.04)
- North America
- Canada > British Columbia
- United States
- California
- Los Angeles County > Long Beach (0.15)
- Santa Clara County > Palo Alto (0.04)
- District of Columbia > Washington (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Maryland > Baltimore (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- New York > New York County
- New York City (0.04)
- California
- Oceania > Australia
- New South Wales > Sydney (0.04)
- Africa > Ethiopia
- Genre:
- Research Report > New Finding (0.48)
- Technology: