# IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification

arXiv: https://arxiv.org/abs/2502.06280 · HTML: https://mlsanity.com/paper/2502.06280/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 54 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 30 of 35)

- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Towards Deeper Graph Neural Networks](https://mlsanity.com/paper/2007.09296/) (2020)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)
- [A Unified View of Label Shift Estimation](https://mlsanity.com/paper/2003.07554/) (2020)
- [Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels](https://mlsanity.com/paper/1902.11038/) (2019)
- [ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs](https://mlsanity.com/paper/2402.11235/) (2024)
- [Topology-Imbalance Learning for Semi-Supervised Node Classification](https://mlsanity.com/paper/2110.04099/) (2021)
- [ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networks](https://mlsanity.com/paper/2106.02817/) (2021)
- [Investigating Why Contrastive Learning Benefits Robustness Against Label Noise](https://mlsanity.com/paper/2201.12498/) (2022)
- [TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2206.12917/) (2022)
- [Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift](https://mlsanity.com/paper/2201.11349/) (2022)
- [GLBench: A Comprehensive Benchmark for Graph with Large Language Models](https://mlsanity.com/paper/2407.07457/) (2024)
- [Model Degradation Hinders Deep Graph Neural Networks](https://mlsanity.com/paper/2206.04361/) (2022)
- [Learning Strong Graph Neural Networks with Weak Information](https://mlsanity.com/paper/2305.18457/) (2023)
- [Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid](https://mlsanity.com/paper/2210.16834/) (2022)
- [GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification](https://mlsanity.com/paper/2302.12814/) (2023)
- [GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2306.09612/) (2023)
- [Graph Sparsification via Mixture of Graphs](https://mlsanity.com/paper/2405.14260/) (2024)
- [The Devil is in the Conflict: Disentangled Information Graph Neural Networks for Fraud Detection](https://mlsanity.com/paper/2210.12384/) (2022)
- [Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation](https://mlsanity.com/paper/2306.10534/) (2023)
- [Rethinking Fair Graph Neural Networks from Re-balancing](https://mlsanity.com/paper/2407.11624/) (2024)

## Built on by (most cited first, 4 of 4)

- [Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects](https://mlsanity.com/paper/2507.21407/) (2025)
- [Preference-driven Knowledge Distillation for Few-shot Node Classification](https://mlsanity.com/paper/2510.10116/) (2025)
- [GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance](https://mlsanity.com/paper/2511.10022/) (2025)
- [GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance](https://mlsanity.com/paper/2601.19352/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved great success in dealing with non-Euclidean graph-structured data and have been widely deployed in many real-world applications. However, their effectiveness is often jeopardized under class-imbalanced training sets. Most existing studies have analyzed class-imbalanced node classification from a supervised learning perspective, but they do not fully utilize the large number of unlabeled nodes in semi-supervised scenarios. We claim that the supervised signal is just the tip of the iceberg and a large number of unlabeled nodes have not yet been effectively utilized. In this work, we propose IceBerg, a debiased self-training framework to address the class-imbalanced and few-shot challenges for GNNs at the same time. Specifically, to figure out the Matthew effect and label distribution shift in self-training, we propose Double Balancing, which can largely improve the performance of existing baselines with just a few lines of code as a simple plug-and-play module. Secondly, to enhance the long-range propagation capability of GNNs, we disentangle the propagation and transformation operations of GNNs. Therefore, the weak supervision signals can propagate more effectively to address the few-shot issue. In summary, we find that leveraging unlabeled nodes can significantly enhance the performance of GNNs in class-imbalanced and few-shot scenarios, and even small, surgical modifications can lead to substantial performance improvements. Systematic experiments on benchmark datasets show that our method can deliver considerable performance gain over existing class-imbalanced node classification baselines. Additionally, due to IceBerg's outstanding ability to leverage unsupervised signals, it also achieves state-of-the-art results in few-shot node classification scenarios. The code of IceBerg is available at: https://github.com/ZhixunLEE/IceBerg.