Continual graph learning (CGL) is purposed to continuously update a graph model with graph data being fed in a streaming manner. Since the model easily forgets previously learned knowledge when training with new-coming data, the catastrophic forgetting problem has been the major focus in CGL. Recent replay-based methods intend to solve this problem by updating the model using both (1) the entire new-coming data and (2) a sampling-based memory bank that stores replayed graphs to approximate the distribution of historical data. After updating the model, a new replayed graph sampled from the incoming graph will be added to the existing memory bank. Despite these methods are intuitive and effective for the CGL, two issues are identified in this paper. Firstly, most sampling-based methods struggle to fully capture the historical distribution when the storage budget is tight. Secondly, a significant data imbalance exists in terms of the scales of the complex new-coming graph data and the lightweight memory bank, resulting in unbalanced training. To solve these issues, a \textit{Condense and Train (CaT)} framework is proposed in this paper. Prior to each model update, the new-coming graph is condensed to a small yet informative synthesised replayed graph, which is then stored in a \textit{Condensed Graph Memory} with historical replay graphs. In the continual learning phase, a \textit{Training in Memory} scheme is used to update the model directly with the \textit{Condensed Graph Memory} rather than the whole new-coming graph, which alleviates the data imbalance problem. Extensive experiments conducted on four benchmark datasets successfully demonstrate superior performances of the proposed CaT framework in terms of effectiveness and efficiency. The code has been released on \url{https://github.com/superallen13/CaT-CGL}.

连续图学习（CGL）旨在用以流式传入的图数据不断更新图模型。本论文提出了一种名为“Condense and Train (CaT)”的框架来解决CGL中存在的数据不平衡和历史分布近似问题，通过对新来的图进行精简并将其存入“Condensed Graph Memory”中，最终通过“Training in Memory”方案来直接更新模型。在四个基准数据集上进行的广泛实验成功证明了所提出的CaT框架在效果和效率上的优越性。

CaT：带有图压缩的平衡渐进式图学习