.png){kind=icon}
.png){kind=icon}
Return
M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification
.png){kind=icon}
OA
AI
DOI：10.1109/TNSE.2020.3032950.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 in the benchmark datasets makes it easy for graph classification models to fall into over-fitting and undergeneralization. To improve this, we introduce data augmentation on graphs (i.e. graph augmentation) and present four methods: random mapping, vertex-similarity mapping, motif-random mapping and motif-similarity mapping, to generate more weakly labeled data for small-scale benchmark datasets via heuristic transformation of graph structures. Furthermore, we propose a generic model evolution framework, named M-Evolve, which combines graph augmentation, data filtration and model retraining to optimize pre-trained graph classifiers. Experiments on six benchmark datasets demonstrate that the proposed framework helps existing graph classification models alleviate over-fitting and undergeneralization in the training on small-scale benchmark datasets, which successfully yields an average improvement of 3-13% accuracy on graph classification tasks.
Keywords:
Kernel
Data models
Benchmark testing
Brain modeling
Reliability
Training
Task analysis
Graph classification
Data augmentation
Model evolution
Vertex similarity
Motif
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
7.9
Papers:
2.5K
Citations:
10.0K