Node Classification of Imbalanced Data Using Ensemble Graph Neural Networks
Source abstract
Abstract
In real-world scenarios, many datasets suffer from class imbalance. For example, on online review platforms, the proportion of fake and genuine comments is often highly skewed. Although existing graph neural network (GNN) models have achieved notable progress in classification tasks, their performance tends to rely on relatively balanced data distributions. To tackle this challenge, we propose an ensemble graph neural network framework designed for imbalanced node classification. Specifically, we employ spectral-based graph convolutional neural networks as base classifiers and train multiple models in parallel. We then adopt a bagging ensemble strategy to integrate the predictions of these classifiers and determine the final classification results through majority voting. Furthermore, we extend this approach to fake review detection tasks. Extensive experiments conducted on imbalanced node classification datasets (Cora and BlogCatalog), as well as fake review detection (YelpChi), demonstrate that our method consistently outperforms state-of-the-art baselines, achieving significant gains in accuracy, AUC, and Macro-F1. Notably, on the Cora dataset, our model improves accuracy and Macro-F1 by 3.4% and 2.3%, respectively, while on the BlogCatalog dataset, it achieves improvements of 2.5%, 1.8%, and 0.5% in accuracy, AUC, and Macro-F1, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Imbalanced Data Classification Techniques · Electricity Theft Detection Techniques · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Information Engineering College, Suqian University, Suqian 223800, China
Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin 541004, China
Funding
Suqian Sci&Tech Program · Guangxi Key Laboratory of Trusted Software
References (51)
Show source-provided references
1. Zhang, S., Yin, H., Chen, T., Nguyen, Q.V.H., Huang, Z., and Cui, L. (2020, January 25–30). GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection. Proceedings of the 43rd international ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, China.10.1145/3397271.3401165 ↗
2. A systematic review of AI-enhanced techniques in credit card fraud detection10.1186/s40537-024-01048-8 ↗
3. Zhong, Q., Liu, Y., Ao, X., Hu, B., Feng, J., Tang, J., and He, Q. (2020, January 20–24). Financial Defaulter Detection on Online Credit Payment via Multi-view Attributed Heterogeneous Information Network. Proceedings of the Web Conference 2020, Taipei, Taiwan.10.1145/3366423.3380159 ↗
4. MGCNRF: Prediction of Disease-Related miRNAs Based on Multiple Graph Convolutional Networks and Random Forest10.1109/TNNLS.2023.3289182 ↗
5. Multiknowledge and LLM-Inspired Heterogeneous Graph Neural Network for Fake News Detection10.1109/TCSS.2024.3488191 ↗
6. DRGCN: Dual Residual Graph Convolutional Network for Hyperspectral Image Classification
7. Zhao, T., Zhang, X., and Wang, S. (2021, January 8–12). GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks. Proceedings of the 14th ACM International Conference on Web Search and Data Mining, Virtual Event, Israel.10.1145/3437963.3441720 ↗
8. SMOTE: Synthetic Minority Over-sampling Technique10.1613/jair.953 ↗
9. Xu, L. (2024). Machine Learning Solutions for Classification and Regions of Interest Analysis on Imbalanced Datasets. [Ph.D. Thesis, University of Tampere].
10. Multi-sensor data fusion for smart healthcare: Optimizing specialty-based classification of imbalanced EMRs10.1016/j.inffus.2025.103503 ↗
11. An efficient boundary prediction method based on multi-fidelity Gaussian classification process for class-imbalance10.1016/j.engappai.2025.110549 ↗
12. Mildenberger, D., Hager, P., Rueckert, D., and Menten, M.J. (2025, January 10–17). A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, Tennessee.10.1109/CVPR52734.2025.00964 ↗
13. A survey on imbalanced learning: Latest research, applications and future directions10.1007/s10462-024-10759-6 ↗
14. A Novel Expandable Borderline Smote Over-Sampling Method for Class Imbalance Problem10.1109/TKDE.2025.3544284 ↗
15. Kachan, O., Savchenko, A.V., and Gusev, G. (2025, January 3–7). Simplicial SMOTE: Oversampling Solution to the Imbalanced Learning Problem. Proceedings of the KDD, Toronto, ON, Canada.10.1145/3690624.3709268 ↗
16. Chang, A., Fontaine, M.C., Booth, S., Mataric, M.J., and Nikolaidis, S. (March, January 25). Quality-Diversity Generative Sampling for Learning with Synthetic Data. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA.
17. Undersampled K-means approach for handling imbalanced distributed data10.1007/s13748-014-0045-6 ↗
18. Cui, Y., Jia, M., Lin, T., Song, Y., and Belongie, S.J. (2019, January 15–20). Class-Balanced Loss Based on Effective Number of Samples. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00949 ↗
19. Lin, T., Goyal, P., Girshick, R.B., He, K., and Dollár, P. (2017, January 22–29). Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
20. Li, B., Liu, Y., and Wang, X. (2019, January 29–31). Gradient Harmonized Single-Stage Detector. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
21. Deterministic Sampling Classifier with weighted Bagging for drifted imbalanced data stream classification10.1016/j.asoc.2022.108855 ↗
22. Jafarzadeh, H., MahdianPari, M., Gill, E., Mohammadimanesh, F., and Homayouni, S. (2021). Bagging and Boosting Ensemble Classifiers for Classification of Multispectral, Hyperspectral and PolSAR Data: A Comparative Evaluation. Remote. Sens., 13.10.3390/rs13214405 ↗
23. Li, J., Zhu, X., and Wang, J. (2023, January 7–14). AdaBoost.C2: Boosting Classifiers Chains for Multi-Label Classification. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.10.1609/aaai.v37i7.26033 ↗
24. BS-SC Model: A Novel Method for Predicting Child Abuse Using Borderline-SMOTE Enabled Stacking Classifier10.32604/csse.2023.034910 ↗
25. DRGCN-BiLSTM: An Electrocardiogram Heartbeat Classification Using Dynamic Spatial-Temporal Graph Convolutional and Bidirectional Long-Short Term Memory Technique10.1109/TCE.2025.3540875 ↗
26. Zhang, L., Yan, X., He, J., Li, R., and Chu, W. (2023, January 7–14). DRGCN: Dynamic Evolving Initial Residual for Deep Graph Convolutional Networks. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.10.1609/aaai.v37i9.26332 ↗
27. A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions10.1109/TKDE.2025.3549299 ↗
28. Ju, W., Mao, Z., Yi, S., Qin, Y., Gu, Y., Xiao, Z., Shen, J., Qiao, Z., and Zhang, M. (25–4, January 25). Cluster-guided Contrastive Class-imbalanced Graph Classification. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA.
29. A Comprehensive Survey on Graph Neural Networks10.1109/TNNLS.2020.2978386 ↗
30. Imbalanced Malware Family Classification Using Multimodal Fusion and Weight Self-Learning10.1109/TITS.2022.3208891 ↗
31. Zeng, L., Li, L., Gao, Z., Zhao, P., and Li, J. (2023, January 7–14). ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification. Proceedings of the AAAI conference on Artificial Intelligence, Washington, DC, USA.10.1609/aaai.v37i9.26319 ↗
32. Zhou, M., and Gong, Z. (2023, January 7–14). GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.10.1609/aaai.v37i4.25622 ↗
33. Imbalanced ensemble learning leveraging a novel data-level diversity metric10.1016/j.patcog.2024.110886 ↗
34. A new data complexity measure for multi-class imbalanced classification tasks10.1016/j.patcog.2024.110881 ↗
35. CenGCN: Centralized Convolutional Networks with Vertex Imbalance for Scale-Free Graphs
36. Chen, Y., and Lu, C. (2023, January 17–24). RankMix: Data Augmentation for Weakly Supervised Learning of Classifying Whole Slide Images with Diverse Sizes and Imbalanced Categories. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.02292 ↗
37. Qu, L., Zhu, H., Zheng, R., Shi, Y., and Yin, H. (2021, January 14–18). ImGAGN: Imbalanced Network Embedding via Generative Adversarial Graph Networks. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Singapore.10.1145/3447548.3467334 ↗
38. Liu, Y., Ao, X., Qin, Z., Chi, J., Feng, J., Yang, H., and He, Q. (2021, January 19–23). Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection. Proceedings of the Web Conference 2021, Ljubljana, Slovenia.10.1145/3442381.3449989 ↗
39. Wu, L., Lin, H., Gao, Z., Tan, C., and Li, S.Z. (2022). GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction. Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer Nature.10.1007/978-3-031-26412-2_32 ↗
40. RAGCN: Region Aggregation Graph Convolutional Network for Bone Age Assessment From X-Ray Images10.1109/TIM.2022.3218574 ↗
41. Sun, K., Zhu, Z., and Lin, Z. (2021, January 3–7). AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models. Proceedings of the ICLR, Virtual Event, Austria.
42. Hamilton, W.L., Ying, Z., and Leskovec, J. (2017, January 4–9). Inductive Representation Learning on Large Graphs. Proceedings of the NIPS, Long Beach, CA, USA.
43. Zeng, H., Zhou, H., Srivastava, A., Kannan, R., and Prasanna, V.K. (2020). GraphSAINT: Graph Sampling Based Inductive Learning Method. arXiv.
44. Liu, Z., Dou, Y., Yu, P.S., Deng, Y., and Peng, H. (2020, January 25–30). Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, China.10.1145/3397271.3401253 ↗
45. Park, J., Song, J., and Yang, E. (2022, January 28). GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification. Available online: https://openreview.net/forum?id=MXEl7i-iru.
46. Makansi, O., Ilg, E., Çiçek, Ö., and Brox, T. (2019, January 16–17). Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00731 ↗
47. Network Embedding with Completely-Imbalanced Labels10.1109/TKDE.2020.2971490 ↗
48. Oh, J., Cho, K., and Bruna, J. (2019). Advancing GraphSAGE with A Data-Driven Node Sampling. arXiv.
49. Barakat, A., and Bianchi, P. (2020, January 18–20). Convergence Rates of a Momentum Algorithm with Bounded Adaptive Step Size for Nonconvex Optimization. Proceedings of the Asian Conference on Machine Learning, Bangkok, Thailand.
50. Kipf, T.N., and Welling, M. (2017, January 24–26). Semi-Supervised Classification with Graph Convolutional Networks. Proceedings of the ICLR, Toulon, France.
51. Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y. (2017). Graph Attention Networks. arXiv.