arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2503.01580cs.LGcs.AI

时序图持续学习的选择性学习方法

A Selective Learning Method for Temporal Graph Continual Learning

Shenzhen Institute of Computing Sciences(深圳计算科学研究院)

Hanmo Liu, Shimin Di, Haoyang Li, Xun Jian, Yue Wang, Lei Chen

AI总结:

针对时序图持续学习(TGCL)中旧类别知识维护问题,提出选择性学习框架LTF,通过子集替代完整数据并优化选择目标以最小化误差,在三个真实数据集上验证了有效性。

摘要:

节点分类是时序图学习(TGL)中的一项关键任务。现实生活中的时序图通常会随着时间的推移引入新的节点类别,但现有的 TGL 方法假设类别集合是固定的。这一假设带来了局限性,因为使用完整数据更新模型代价高昂,而仅关注新类别会导致遗忘旧类别。图持续学习(GCL)方法通过使用旧类别子集来缓解遗忘问题,但未能考虑它们的演化。我们将这一新颖问题定义为时序图持续学习(TGCL),其重点在于高效维护旧类别的最新知识。为了解决 TGCL,我们提出了一种选择性学习框架,用子集替代旧类别数据,称为面向未来学习(LTF)。我们推导了这种替换所导致误差的上界,并将其转化为选择和学习子集的目标,从而在最小化分类误差的同时保留完整旧类别数据的分布。在三个真实世界数据集上的实验验证了 LTF 在 TGCL 上的有效性。

英文摘要:

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.

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。

↑