Journal
KNOWLEDGE-BASED SYSTEMS
Volume 228, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.knosys.2021.107301
Keywords
Graph representation; Graph classification; Feature learning
Categories
Funding
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China [11201019, 62050132]
- International Cooperation Project, China [2010DFR00700]
- Fundamental Research of Civil Aircraft, China [MJ-F-2012-04]
- Beijing Natural Science Foundation [1192012, Z180005]
Ask authors/readers for more resources
The paper introduces a novel graph embedding algorithm named GraphCSC, which integrates skeleton information and component information of graphs into embeddings for classification. Experiments demonstrate that the algorithm outperforms state-of-the-art baselines in graph classification tasks.
Most existing popular methods for learning graph embedding only consider fixed-order global structural features but lack hierarchical representation for structures. To address this weakness, we propose a novel graph embedding algorithm named GraphCSC that realizes classification leveraging skeleton information from anonymous random walks with fixed-order length, and component information derived from subgraphs with different sizes. Two graphs are similar if their skeletons and components are both similar. Thus in our model, we integrate both of them together into embeddings as graph homogeneity characterization. We demonstrate our model on different datasets in comparison with a comprehensive list of up-to-date state-of-the-art baselines, and experiments show that our work is superior in real-world graph classification tasks. (C) 2021 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available