GDM: Dual Mixup for Graph Classification with Limited Supervision

by   Abdullah Alchihabi, et al.

Graph Neural Networks (GNNs) require a large number of labeled graph samples to obtain good performance on the graph classification task. The performance of GNNs degrades significantly as the number of labeled graph samples decreases. To reduce the annotation cost, it is therefore important to develop graph augmentation methods that can generate new graph instances to increase the size and diversity of the limited set of available labeled graph samples. In this work, we propose a novel mixup-based graph augmentation method, Graph Dual Mixup (GDM), that leverages both functional and structural information of the graph instances to generate new labeled graph samples. GDM employs a graph structural auto-encoder to learn structural embeddings of the graph samples, and then applies mixup to the structural information of the graphs in the learned structural embedding space and generates new graph structures from the mixup structural embeddings. As for the functional information, GDM applies mixup directly to the input node features of the graph samples to generate functional node feature information for new mixup graph instances. Jointly, the generated input node features and graph structures yield new graph samples which can supplement the set of original labeled graphs. Furthermore, we propose two novel Balanced Graph Sampling methods to enhance the balanced difficulty and diversity for the generated graph samples. Experimental results on the benchmark datasets demonstrate that our proposed method substantially outperforms the state-of-the-art graph augmentation methods when the labeled graphs are scarce.


page 1

page 2

page 3

page 4


Dual GNNs: Graph Neural Network Learning with Limited Supervision

Graph Neural Networks (GNNs) require a relatively large number of labele...

GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks

Node classification is an important research topic in graph learning. Gr...

Graph Attention Networks with Positional Embeddings

Graph Neural Networks (GNNs) are deep learning methods which provide the...

GRAFICS: Graph Embedding-based Floor Identification Using Crowdsourced RF Signals

We study the problem of floor identification for radiofrequency (RF) sig...

EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost

Graph-based models have become increasingly important in various domains...

M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification

Graph classification, which aims to identify the category labels of grap...

Graph Augmentation Clustering Network

Existing graph clustering networks heavily rely on a predefined graph an...

Please sign up or login with your details

Forgot password? Click here to reset