持续图学习：综述
Continual Graph Learning: A Survey
AI总结：
本文综述了持续图学习的核心方法与挑战，提出基于对抗的生成性重放框架，提升分布匹配与稳定性。
摘要：
持续图学习（CGL）使模型能够从流式图结构数据中逐步学习，而不会遗忘之前的知识。经验回放是一种常见解决方案，但可能导致信息丢失和隐私风险。生成性回放通过合成信息子图来解决这些问题。现有生成性回放方法通常依赖于通过分布匹配进行图压缩，面临两个关键挑战：（1）随机特征编码可能无法捕捉差异度度量的特征内核，削弱分布对齐；（2）在固定小子图上的匹配无法保证先前任务的低风险，如领域适应理论所示。为克服这些限制，我们提出了基于对抗的生成性回放（ACGR）框架。它将图压缩重新表述为min-max优化问题以实现更好的分布匹配。此外，我们学习子图的分布而非单一子图，允许生成多个样本并改进经验风险最小化。在三个基准数据集上的实验表明，ACGR在准确性和稳定性上均优于现有方法。
英文摘要：
Continual Graph Learning (CGL) enables models to incrementally learn from streaming graph-structured data without forgetting previously acquired knowledge. Experience replay is a common solution that reuses a subset of past samples during training. However, it may lead to information loss and privacy risks. Generative replay addresses these concerns by synthesizing informative subgraphs for rehearsal. Existing generative replay approaches often rely on graph condensation via distribution matching, which faces two key challenges: (1) the use of random feature encodings may fail to capture the characteristic kernel of the discrepancy metric, weakening distribution alignment; and (2) matching over a fixed small subgraph cannot guarantee low risk on previous tasks, as indicated by domain adaptation theory. To overcome these limitations, we propose an Adversarial Condensation based Generative Replay (ACGR) framwork. It reformulates graph condensation as a min-max optimization problem to achieve better distribution matching. Moreover, instead of learning a single subgraph, we learn its distribution, allowing for the generation of multiple samples and improved empirical risk minimization. Experiments on three benchmark datasets demonstrate that ACGR outperforms existing methods in both accuracy and stability.
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。
