Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification

About

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.

Wen-Zhi Li, Chang-Dong Wang, Hui Xiong, Jian-Huang Lai• 2023

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora standard (test)
Accuracy78.35
130
Node ClassificationCora
AUC95
65
Node ClassificationPhoto
AUC96.24
38
Node ClassificationComputers
AUC96.53
38
Node ClassificationPubmed standard (test)
Accuracy77.11
13
Node ClassificationPubmed
AUC0.8967
13
Node ClassificationPhoto standard (test)
Accuracy84.52
13
Node ClassificationComputers standard (test)
Acc82.78
13
Node ClassificationCiteseer
AUC88.35
13
Node ClassificationWiki CS
AUC95.93
13
Showing 10 of 22 rows

Other info

Follow for update