UNREAL:Unlabeled Nodes Retrieval and Labeling for Heavily-imbalanced Node Classification

03/18/2023
by   Liang Yan, et al.
0

Extremely skewed label distributions are common in real-world node classification tasks. If not dealt with appropriately, it significantly hurts the performance of GNNs in minority classes. Due to its practical importance, there have been a series of recent research devoted to this challenge. Existing over-sampling techniques smooth the label distribution by generating “fake” minority nodes and synthesizing their features and local topology, which largely ignore the rich information of unlabeled nodes on graphs. In this paper, we propose UNREAL, an iterative over-sampling method. The first key difference is that we only add unlabeled nodes instead of synthetic nodes, which eliminates the challenge of feature and neighborhood generation. To select which unlabeled nodes to add, we propose geometric ranking to rank unlabeled nodes. Geometric ranking exploits unsupervised learning in the node embedding space to effectively calibrates pseudo-label assignment. Finally, we identify the issue of geometric imbalance in the embedding space and provide a simple metric to filter out geometrically imbalanced nodes. Extensive experiments on real-world benchmark datasets are conducted, and the empirical results show that our method significantly outperforms current state-of-the-art methods consistent on different datasets with different imbalance ratios.

READ FULL TEXT
research
06/10/2022

Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks

In recent years, graph neural networks (GNNs) have achieved state-of-the...
research
10/22/2021

Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification

Recent years have witnessed the significant success of applying graph ne...
research
04/28/2023

Imbalanced Node Classification Beyond Homophilic Assumption

Imbalanced node classification widely exists in real-world networks wher...
research
06/21/2021

GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction

Recent years have witnessed great success in handling node classificatio...
research
10/22/2018

Introducing Curvature to the Label Space

One-hot encoding is a labelling system that embeds classes as standard b...
research
04/11/2023

Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification

Learning unbiased node representations for imbalanced samples in the gra...
research
11/27/2022

ReGrAt: Regularization in Graphs using Attention to handle class imbalance

Node classification is an important task to solve in graph-based learnin...

Please sign up or login with your details

Forgot password? Click here to reset