UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913110320742400 |
|---|---|
| author | Zhang, Danhui Wang, Zhe Qing, Qing Liu, Jiarui Gao, Wentao Xu, Ziqi Hou, Mingliang Zhang, Xikun Luo, Renqiang |
| author_facet | Zhang, Danhui Wang, Zhe Qing, Qing Liu, Jiarui Gao, Wentao Xu, Ziqi Hou, Mingliang Zhang, Xikun Luo, Renqiang |
| contents | Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve over time. However, existing CGL methods largely assume clean supervision and overlook a critical challenge: the newly arriving portions of the graph are often noisy, due to annotation errors or adversarial corruption. This mismatch limits their applicability in practice. In this work, we study robust continual graph learning, where models must simultaneously handle catastrophic forgetting and noisy supervision in evolving graph data. We show that label noise introduces a new failure mode, catastrophic remembering, where models persistently reinforce corrupted knowledge across tasks. To address these challenges, we propose a Unified Flow-Oriented framework (UFO). First, UFO models conditional feature distributions via flow-based generative modeling and produces replay representations, mitigating forgetting without storing historical data. Second, UFO estimates instance-level reliability scores to distinguish clean from noisy nodes, reducing the impact of corrupted supervision and alleviating catastrophic remembering. Extensive experiments on four benchmark graph datasets under varying noise ratios demonstrate that UFO consistently outperforms existing methods in both accuracy and forgetting metrics. Code is available at: https://anonymous.4open.science/r/UFO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09862 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning Zhang, Danhui Wang, Zhe Qing, Qing Liu, Jiarui Gao, Wentao Xu, Ziqi Hou, Mingliang Zhang, Xikun Luo, Renqiang Machine Learning Artificial Intelligence Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve over time. However, existing CGL methods largely assume clean supervision and overlook a critical challenge: the newly arriving portions of the graph are often noisy, due to annotation errors or adversarial corruption. This mismatch limits their applicability in practice. In this work, we study robust continual graph learning, where models must simultaneously handle catastrophic forgetting and noisy supervision in evolving graph data. We show that label noise introduces a new failure mode, catastrophic remembering, where models persistently reinforce corrupted knowledge across tasks. To address these challenges, we propose a Unified Flow-Oriented framework (UFO). First, UFO models conditional feature distributions via flow-based generative modeling and produces replay representations, mitigating forgetting without storing historical data. Second, UFO estimates instance-level reliability scores to distinguish clean from noisy nodes, reducing the impact of corrupted supervision and alleviating catastrophic remembering. Extensive experiments on four benchmark graph datasets under varying noise ratios demonstrate that UFO consistently outperforms existing methods in both accuracy and forgetting metrics. Code is available at: https://anonymous.4open.science/r/UFO. |
| title | UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.09862 |