Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification

10/22/2021
by   Yu Wang, et al.
0

Recent years have witnessed the significant success of applying graph neural networks (GNNs) in learning effective node representations for classification. However, current GNNs are mostly built under the balanced data-splitting, which is inconsistent with many real-world networks where the number of training nodes can be extremely imbalanced among the classes. Thus, directly utilizing current GNNs on imbalanced data would generate coarse representations of nodes in minority classes and ultimately compromise the classification performance. This therefore portends the importance of developing effective GNNs for handling imbalanced graph data. In this work, we propose a novel Distance-wise Prototypical Graph Neural Network (DPGNN), which proposes a class prototype-driven training to balance the training loss between majority and minority classes and then leverages distance metric learning to differentiate the contributions of different dimensions of representations and fully encode the relative position of each node to each class prototype. Moreover, we design a new imbalanced label propagation mechanism to derive extra supervision from unlabeled nodes and employ self-supervised learning to smooth representations of adjacent nodes while separating inter-class prototypes. Comprehensive node classification experiments and parameter analysis on multiple networks are conducted and the proposed DPGNN almost always significantly outperforms all other baselines, which demonstrates its effectiveness in imbalanced node classification. The implementation of DPGNN is available at <https://github.com/YuWVandy/DPGNN>.

READ FULL TEXT
research
12/01/2021

Imbalanced Graph Classification via Graph-of-Graph Neural Networks

Graph Neural Networks (GNNs) have achieved unprecedented success in lear...
research
06/15/2022

CLNode: Curriculum Learning for Node Classification

Node classification is a fundamental graph-based task that aims to predi...
research
05/23/2022

ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification

Graph contrastive learning (GCL) has attracted a surge of attention due ...
research
03/18/2023

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

Extremely skewed label distributions are common in real-world node class...
research
08/22/2022

LTE4G: Long-Tail Experts for Graph Neural Networks

Existing Graph Neural Networks (GNNs) usually assume a balanced situatio...
research
02/24/2023

GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification

Graph neural networks (GNNs) have achieved great success in node classif...
research
05/30/2021

How effective are Graph Neural Networks in Fraud Detection for Network Data?

Graph-based Neural Networks (GNNs) are recent models created for learnin...

Please sign up or login with your details

Forgot password? Click here to reset