联邦持续图学习
Federated Continual Graph Learning
AI总结：
针对演化图数据中的存储隐私问题与灾难性遗忘，提出联邦持续图学习框架POWER，通过保留经验节点和伪原型重建解决局部遗忘与全局专长冲突，显著优于现有基线方法。
摘要：
管理不断演化的图数据在存储和隐私方面带来了巨大挑战，在此类数据上训练图神经网络（GNNs）通常会导致灾难性遗忘，损害在早期任务上的性能。尽管现有的持续图学习（CGL）方法在一定程度上缓解了这一问题，但它们依赖于中心化架构，并忽略了分布式图数据库利用集体智能的潜力。为此，我们提出了联邦持续图学习（FCGL），旨在在存储和隐私约束下使GNNs适应多个不断演化的图。我们的实证研究突出了两个核心挑战：一是局部图遗忘（LGF），即客户端在适应新任务时会丢失先前的知识；二是全局专长冲突（GEC），即由于服务器端参数聚合期间客户端专长不一致，全局GNN在适应新任务和保留旧任务上均表现出次优性能。为解决这些问题，我们引入了POWER框架，该框架在本地保留具有最大局部-全局覆盖率的经验节点以缓解LGF，并利用伪原型重建与轨迹感知知识转移来解决GEC。在多种图数据集上的实验表明，POWER优于CGL基线的联邦适应方案以及以视觉为中心的联邦持续学习方法。
英文摘要：
Managing evolving graph data presents substantial challenges in storage and privacy, and training graph neural networks (GNNs) on such data often leads to catastrophic forgetting, impairing performance on earlier tasks. Despite existing continual graph learning (CGL) methods mitigating this to some extent, they rely on centralized architectures and ignore the potential of distributed graph databases to leverage collective intelligence. To this end, we propose Federated Continual Graph Learning (FCGL) to adapt GNNs across multiple evolving graphs under storage and privacy constraints. Our empirical study highlights two core challenges: local graph forgetting (LGF), where clients lose prior knowledge when adapting to new tasks, and global expertise conflict (GEC), where the global GNN exhibits sub-optimal performance in both adapting to new tasks and retaining old ones, arising from inconsistent client expertise during server-side parameter aggregation. To address these, we introduce POWER, a framework that preserves experience nodes with maximum local-global coverage locally to mitigate LGF, and leverages pseudo-prototype reconstruction with trajectory-aware knowledge transfer to resolve GEC. Experiments on various graph datasets demonstrate POWER's superiority over federated adaptations of CGL baselines and vision-centric federated continual learning approaches.
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。
