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.

翻译：连续图学习能够使模型逐步从流式图结构数据中学习，同时不遗忘先前获得的知识。经验回放是一种常用解决方案，在训练过程中重复使用部分历史样本。然而，这可能导致信息丢失和隐私风险。生成式回放通过合成信息性子图进行重演来应对这些问题。现有生成式回放方法通常依赖于通过分布匹配的图压缩技术，但面临两个关键挑战：(1) 使用随机特征编码可能无法捕捉差异度量的特征核，从而削弱分布对齐效果；(2) 根据领域适应理论，在固定小子图上进行匹配无法确保对先前任务具有低风险。为克服这些局限，我们提出一种基于对抗压缩的生成式回放框架。该框架将图压缩重新表述为极小极大优化问题，以实现更优的分布匹配。此外，我们不再学习单一子图，而是学习其分布，从而能够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，该方法在准确性和稳定性方面均优于现有方法。