ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2110.08690
30
6

Tackling the Imbalance for GNNs

17 October 2021
Rui Wang
Weixuan Xiong
Qing-Hu Hou
Ou Wu
ArXivPDFHTML
Abstract

Different from deep neural networks for non-graph data classification, graph neural networks (GNNs) leverage the information exchange between nodes (or samples) when representing nodes. The category distribution shows an imbalance or even a highly-skewed trend on nearly all existing benchmark GNN data sets. The imbalanced distribution will cause misclassification of nodes in the minority classes, and even cause the classification performance on the entire data set to decrease. This study explores the effects of the imbalance problem on the performances of GNNs and proposes new methodologies to solve it. First, a node-level index, namely, the label difference index (LDILDILDI), is defined to quantitatively analyze the relationship between imbalance and misclassification. The less samples in a class, the higher the value of its average LDILDILDI; the higher the LDILDILDI of a sample, the more likely the sample will be misclassified. We define a new loss and propose four new methods based on LDILDILDI. Experimental results indicate that the classification accuracies of the three among our proposed four new methods are better in both transductive and inductive settings. The LDILDILDI can be applied to other GNNs.

View on arXiv
Comments on this paper