UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning

TL;DR

UFO introduces a flow-based framework for robust continual graph learning, effectively handling noisy supervision and catastrophic forgetting without storing historical data, demonstrated through extensive benchmark experiments.

Contribution

The paper presents a novel unified flow-oriented framework (UFO) that addresses noise and forgetting in continual graph learning, a challenge not tackled by prior methods.

Findings

UFO outperforms existing methods in accuracy across multiple datasets.

UFO effectively reduces catastrophic forgetting in noisy environments.

The framework accurately distinguishes clean from noisy nodes, improving robustness.

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.