KLCE: Regularized Imbalance Node-classification Via KL-divergence and Cross-Entropy

Mohammad Taha Teimuri Jervakani, zahra dehghanian, Gholamali Aminian, Hamid R. Rabiee

Keywords: Imbalance classification, node classification, graph neural networks

TL;DR: We introduce a novel regularization based on KL-divergence and cross-entropy for imbalance node classification via Graph neural networks.

Abstract: This paper introduces a novel regularization based on KL-divergence and cross-entropy for imbalance node classification via Graph neural networks. We evaluate the performance of our approach on several benchmark datasets and compare it with state-of-the-art methods. The experimental results demonstrate the effectiveness of our proposed method in addressing imbalance node classification tasks.

Submission Number: 154