Data Augmentation for Graph Classification
Authors:
Open Access
- 19 October 2020
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2341-2344
Abstract
Graph classification, which aims to identify the category labels of graphs, plays a significant role in drug classification, toxicity detection, protein analysis etc. However, the limitation of scale of benchmark datasets makes it easy for graph classification models to fall into over-fitting and undergeneralization. Towards this, we introduce data augmentation on graphs and present two heuristic algorithms: \emrandom mapping and \emmotif-similarity mapping, to generate more weakly labeled data for small-scale benchmark datasets via heuristic modification of graph structures. Furthermore, we propose a generic model evolution framework, named \emM-Evolve, which combines graph augmentation, data filtration and model retraining to optimize pre-trained graph classifiers. Experiments conducted on six benchmark datasets demonstrate that \emM-Evolve helps existing graph classification models alleviate over-fitting when training on small-scale benchmark datasets and %achieve significant improvement of classification performance. yields an average improvement of 3-12% accuracy on graph classification tasks.Keywords
All Related Versions
Funding Information
- Zhejiang Provincial Natural Science Foundation of China (LR19F030001)
- National Natural Science Foundation of China (61973273)
This publication has 5 references indexed in Scilit:
- gl2vec2019
- NetLSD2018
- Deep Graph Kernels2015
- Predicting missing links via local informationThe European Physical Journal B, 2009
- Protein function prediction via graph kernelsBioinformatics, 2005