GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning
Not on the map. Why?
Abstract (arXiv)
The class imbalance problem refers to the disproportionate distribution of samples across different classes within a dataset, where the minority classes are significantly underrepresented. This issue is also prevalent in graph-structured data. Most graph neural networks (GNNs) implicitly assume a balanced class distribution and therefore often fail to account for the challenges introduced by class imbalance, which can lead to biased learning and degraded performance on minority classes. We identify a quality inconsistency problem in synthesized nodes, which leads to suboptimal performance under graph imbalance conditions. To mitigate this issue, we propose GraphIFE (Graph Invariant Feature Extraction), a novel framework designed to mitigate quality inconsistency in synthesized nodes. Our approach incorporates two key concepts from graph invariant learning and introduces strategies to strengthen the embedding space representation, thereby enhancing the model's ability to identify invariant features. Extensive experiments demonstrate the framework's efficiency and robust generalization, as GraphIFE consistently outperforms various baselines across multiple datasets. The code is publicly available at https://github.com/flzeng1/GraphIFE.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 28 Sep 2025.
Builds on
32 of 48 references.
References · 32
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2022Generative Adversarial Networkscited by 5,627
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
- 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
- 2018End-to-End Multi-Task Learning with Attentioncited by 534
- 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
- 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
- 2022How Powerful are Spectral Graph Neural Networkscited by 169
- 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
20 more
- 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
- 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 87
- 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
- 2021Topology-Imbalance Learning for Semi-Supervised Node Classificationcited by 56
- 2021ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networkscited by 51
- 2022TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classificationcited by 41
- 2021ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregationcited by 39
- 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
- 2023Class-Imbalanced Graph Learning without Class Rebalancingcited by 29
- 2022ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classificationcited by 21
- 2022Graph Neural Network with Curriculum Learning for Imbalanced Node Classificationcited by 19
- 2023Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalizationcited by 18
- 2023GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classificationcited by 17
- 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
- 2023Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decompositioncited by 13
- 2021Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classescited by 11
- 2021IMBENS: Ensemble Class-imbalanced Learning in Pythoncited by 6
- 2024Graph Contrastive Invariant Learning from the Causal Perspectivecited by 6
- 2024Dissecting the Failure of Invariant Learning on Graphscited by 5
- 2024Prompt-based Unifying Inference Attack on Graph Neural Networkscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.