Author:
Markwald Marco,Demidova Elena
Abstract
AbstractImbalanced graph node classification is a highly relevant and challenging problem in many real-world applications. The inherent data scarcity, a central characteristic of this task, substantially limits the performance of neural classification models driven solely by data. Given the limited instances of relevant nodes and complex graph structures, current methods fail to capture the distinct characteristics of node attributes and graph patterns within the underrepresented classes. In this article, we propose REFUEL—a novel approach for highly imbalanced node classification problems in graphs. Whereas symbolic and neural methods have complementary strengths and weaknesses when applied to such problems, REFUEL combines the power of symbolic and neural learning in a novel neural rule-extraction architecture. REFUEL captures the class semantics in the automatically extracted rule vectors. Then, REFUEL augments the graph nodes with the extracted rules vectors and adopts a Graph Attention Network-based neural node embedding, enhancing the downstream neural node representation. Our evaluation confirms the effectiveness of the proposed REFUEL approach for three real-world datasets with different minority class sizes. REFUEL achieves at least a 4% point improvement in precision on the minority classes of 1.5–2% compared to the baselines.
Funder
Bundesministerium für Wirtschaft und Klimaschutz
Rheinische Friedrich-Wilhelms-Universität Bonn
Publisher
Springer Science and Business Media LLC
Reference24 articles.
1. Alarab, I., Prakoonwit, S., & Nacer, M. I. (2020). Competence of graph convolutional networks for anti-money laundering in bitcoin blockchain. In Proceedings of the 2020 5th international conference on machine learning technologies (pp. 23–27).
2. Bénard, C., Biau, G., Veiga, S. D., & Scornet, E. (2021). Interpretable random forests via rule extraction. In The 24th international conference on artificial intelligence and statistics, Volume 130 of Proceedings of Machine Learning Research (pp. 937–945).
3. Bojchevski, A., & Günnemann, S. (2018). Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. In Proceedings of the 6th International Conference on Learning Representations. OpenReview.net.
4. Bologna, G. (2021). A rule extraction technique applied to ensembles of neural networks, random forests, and gradient-boosted trees. Algorithms, 14(12), 339. https://doi.org/10.3390/A14120339
5. Boruah, A. N., Biswas, S. K., & Bandyopadhyay, S. (2022). Rule extraction from decision tree: Transparent expert system of rules. Concurrency and Computation: Practice and Experience, 34(15), e6935. https://doi.org/10.1002/CPE.6935