GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916974540357632 |
|---|---|
| author | Zeng, Fanlong Gan, Wensheng Yu, Philip S. |
| author_facet | Zeng, Fanlong Gan, Wensheng Yu, Philip S. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23616 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning Zeng, Fanlong Gan, Wensheng Yu, Philip S. Machine Learning Artificial Intelligence 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. |
| title | GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.23616 |