Many real-world graph learning tasks require handling dynamic graphs where new nodes and edges emerge. Dynamic graph learning methods commonly suffer from the catastrophic forgetting problem, where knowledge learned for previous graphs is overwritten by updates for new graphs. To alleviate the problem, continual graph learning methods are proposed. However, existing continual graph learning methods aim to learn new patterns and maintain old ones with the same set of parameters of fixed size, and thus face a fundamental tradeoff between both goals. In this paper, we propose Parameter Isolation GNN (PI-GNN) for continual learning on dynamic graphs that circumvents the tradeoff via parameter isolation and expansion. Our motivation lies in that different parameters contribute to learning different graph patterns. Based on the idea, we expand model parameters to continually learn emerging graph patterns. Meanwhile, to effectively preserve knowledge for unaffected patterns, we find parameters that correspond to them via optimization and freeze them to prevent them from being rewritten. Experiments on eight real-world datasets corroborate the effectiveness of PI-GNN compared to state-of-the-art baselines.

翻译：许多现实世界的图学习任务需要处理新节点和新边不断出现的动态图。动态图学习方法通常面临灾难性遗忘问题，即先前图结构学到的知识会被新图结构的更新所覆盖。为缓解该问题，持续图学习方法被提出。然而，现有持续图学习方法旨在用固定大小的同一组参数同时学习新模式并维持旧模式，因此面临两者之间的根本性权衡。本文提出用于动态图持续学习的参数隔离图神经网络（PI-GNN），通过参数隔离与扩展规避了该权衡。我们的动机在于不同参数对学习不同图模式的贡献存在差异。基于此思想，我们扩展模型参数以持续学习新兴图模式。同时，为有效保留未受影响模式的知识，我们通过优化定位对应这些模式的参数，并通过冻结方式防止其被覆写。在八个真实数据集上的实验验证了PI-GNN相较于最先进基线的有效性。