UFO：一种统一的流导向框架，用于鲁棒的持续图学习
UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
AI总结：
本文提出UFO框架，解决持续图学习中噪声标注和灾难性遗忘问题，通过流基于生成建模和实例可靠性评分提升模型鲁棒性。
摘要：
图学习研究日益转向持续图学习（CGL），以反映真实世界中图不断演变的场景。然而，现有CGL方法大多假设干净的监督，忽视了一个关键挑战：新到达的图部分往往嘈杂，由于标注错误或对抗性污染。这种不匹配限制了其在实践中的应用。本文研究了鲁棒的持续图学习，其中模型必须同时处理灾难性遗忘和嘈杂监督。我们证明标签噪声引入了新的失败模式，即灾难性记忆，其中模型在任务之间持续强化被污染的知识。为了解决这些挑战，我们提出了统一的流导向框架（UFO）。首先，UFO通过流基于生成建模建模条件特征分布，并生成重放表示，从而在不存储历史数据的情况下缓解遗忘。其次，UFO估计实例级别的可靠性分数以区分干净和嘈杂的节点，减少被污染监督的影响并缓解灾难性记忆。在四个基准图数据集上进行的广泛实验表明，UFO在准确性和遗忘度量上都优于现有方法。代码可在：https://anonymous.4open.science/r/UFO。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
