通用图持续学习
Universal Graph Continual Learning
AI总结：
针对图学习的灾难性遗忘问题，提出一种支持节点/图分类多任务的通用图持续学习方法，通过维持图结构一致性的回放机制保留旧知识，在真实数据集上较基线模型的平均性能与遗忘表现均有显著提升。
摘要：
我们针对数据在不同图分布间迁移时图学习出现的灾难性遗忘问题展开研究。现有研究主要解决节点分类增量等单一图持续学习场景，而我们聚焦一种通用范式：任务中的每个数据点可以是节点或图，任务类型涵盖节点分类到图分类。我们提出一种新方法，让图神经网络（GNN）在该通用场景下表现优异。该方法通过 rehearsal（回放）机制保留过往任务的知识，维持图之间的局部与全局结构一致性。我们在真实世界图数据集上，将该方法与多种持续学习基线模型进行对比测试，结果显示其在任务平均性能和遗忘程度上均实现显著提升。
英文摘要：
We address catastrophic forgetting issues in graph learning as incoming data transits from one to another graph distribution. Whereas prior studies primarily tackle one setting of graph continual learning such as incremental node classification, we focus on a universal approach wherein each data point in a task can be a node or a graph, and the task varies from node to graph classification. We propose a novel method that enables graph neural networks to excel in this universal setting. Our approach perseveres knowledge about past tasks through a rehearsal mechanism that maintains local and global structure consistency across the graphs. We benchmark our method against various continual learning baselines in real-world graph datasets and achieve significant improvement in average performance and forgetting across tasks.
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。
