解决动态图中旧类别遗忘问题，用子集高效更新模型。
A Selective Learning Method for Temporal Graph Continual Learning
- 用子集替代旧类别全量数据，降低存储与计算成本。
- 理论推导误差上界，指导子集选择以减少分类错误。
- 适合需要持续学习新类别的实时图分析场景。
节点分类是时序图学习（TGL）的关键任务。现实中的时序图会随时间引入新节点类别，但现有TGL方法假设类别集合固定，这带来局限：用全量数据更新模型代价高，仅关注新类别又会导致遗忘旧类别。图持续学习（GCL）方法通过使用旧类别子集缓解遗忘，但未考虑其演化过程。我们提出新的问题——时序图持续学习（TGCL），旨在高效保持旧类别的最新知识。为此，我们设计了一种选择性学习框架，名为面向未来的学习（LTF），用旧类别子集替代全量数据。我们推导了替换带来的误差上界，并转化为子集选择与学习的目标，以最小化分类误差并保留完整旧类别数据分布。在三个真实数据集上的实验验证了LTF在TGCL任务中的有效性。
原文摘要 · Abstract (English)
Node classification is a key task in temporal graph learning (TGL). Real-life temporal graphs often introduce new node classes over time, but existing TGL methods assume a fixed set of classes. This assumption brings limitations, as updating models with full data is costly, while focusing only on new classes results in forgetting old ones. Graph continual learning (GCL) methods mitigate forgetting using old-class subsets but fail to account for their evolution. We define this novel problem as temporal graph continual learning (TGCL), which focuses on efficiently maintaining up-to-date knowledge of old classes. To tackle TGCL, we propose a selective learning framework that substitutes the old-class data with its subsets, Learning Towards the Future (LTF). We derive an upper bound on the error caused by such replacement and transform it into objectives for selecting and learning subsets that minimize classification error while preserving the distribution of the full old-class data. Experiments on three real-world datasets validate the effectiveness of LTF on TGCL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。