CaT：基于图压缩的均衡持续图学习
CaT: Balanced Continual Graph Learning with Graph Condensation
AI总结：
本文提出CaT框架，通过将新到达图压缩为小型合成回放图并存入压缩图记忆，结合记忆内训练方案，缓解持续图学习中的灾难性遗忘和数据不平衡问题，在多个基准数据集上验证了其有效性与效率。
摘要：
持续图学习（CGL）旨在以流式方式输入图数据，持续更新图模型。由于模型在使用新到达数据进行训练时容易遗忘先前学到的知识，灾难性遗忘问题一直是CGL的主要关注点。近期基于回放的方法试图通过同时使用（1）全部新到达数据和（2）一个基于采样的记忆库来更新模型，该记忆库存储回放图以近似历史数据的分布，从而解决这一问题。在更新模型后，从新到达图中采样得到的新回放图将被添加到现有记忆库中。尽管这些方法对CGL直观且有效，本文仍指出其中存在的两个问题。首先，当存储预算紧张时，大多数基于采样的方法难以充分捕捉历史分布。其次，复杂的新到达图数据与轻量级记忆库在规模上存在显著的数据不平衡，导致训练不均衡。为解决这些问题，本文提出了压缩与训练（CaT）框架。在每次模型更新之前，新到达图被压缩为一个小型但信息丰富的合成回放图，然后将其与历史回放图一起存储在压缩图记忆中。在持续学习阶段，采用记忆内训练方案，直接使用压缩图记忆而非整个新到达图来更新模型，从而缓解数据不平衡问题。在四个基准数据集上进行的大量实验成功证明了所提出的CaT框架在有效性和效率方面的优越性能。代码已发布在 https://github.com/superallen13/CaT-CGL。
英文摘要：
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 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 Condensed Graph Memory with historical replay graphs. In the continual learning phase, a Training in Memory scheme is used to update the model directly with the 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 https://github.com/superallen13/CaT-CGL.
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。
