UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
2026-05-11 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors focus on continual graph learning, where graph data changes over time, but they highlight a common problem: new graph parts often have wrong labels or noise, which previous methods ignored. They discovered that this noise can cause models to repeatedly remember wrong information, a problem they call catastrophic remembering. To fix this, the authors created a method called UFO that uses a special modeling technique to remember old information without saving all past data and identifies unreliable (noisy) parts in the graph to reduce their negative effect. Their experiments show UFO works better than past methods in handling noise and forgetting.
Continual Graph LearningCatastrophic ForgettingLabel NoiseCatastrophic RememberingFlow-based Generative ModelingReplay RepresentationsNoisy SupervisionInstance-level ReliabilityGraph DatasetsRobust Learning
Authors
Danhui Zhang, Zhe Wang, Qing Qing, Jiarui Liu, Wentao Gao, Ziqi Xu, Mingliang Hou, Xikun Zhang, Renqiang Luo
Abstract
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.