Scalable Graph Classification via Random Walk Fingerprints (Extended Abstract)
Abstract
We design a lightweight structural feature extraction technique for graph classification. It leverages node subsets and connection strength reflected by random-walk-based heuristics, presenting a scalable, unsupervised, and easily interpretable alternative. We provide theoretical insights into our technical design and establish a relation between the extracted structural features and the graph spectrum. We show our method achieves high levels of computational efficiency while maintaining robust classification accuracy.
Cite
Text
Li et al. "Scalable Graph Classification via Random Walk Fingerprints (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/1215Markdown
[Li et al. "Scalable Graph Classification via Random Walk Fingerprints (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/li2025ijcai-scalable-a/) doi:10.24963/IJCAI.2025/1215BibTeX
@inproceedings{li2025ijcai-scalable-a,
title = {{Scalable Graph Classification via Random Walk Fingerprints (Extended Abstract)}},
author = {Li, Peiyan and Wang, Honglian and Böhm, Christian},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2025},
pages = {10912-10915},
doi = {10.24963/IJCAI.2025/1215},
url = {https://mlanthology.org/ijcai/2025/li2025ijcai-scalable-a/}
}