动态图连续学习的凝缩-拼接框架
Condensation-Concatenation Framework for Dynamic Graph Continual Learning
AI总结：
本文提出CCC框架，通过凝缩历史图快照与选择性拼接当前图表示，有效解决动态图连续学习中的灾难性遗忘问题，并在多个数据集上验证了其优越性。
摘要：
动态图在现实世界中普遍存在，其中持续的结构变化会在图神经网络（GNNs）中导致灾难性遗忘。尽管连续学习已扩展到动态图，但现有方法忽略了拓扑变化对现有节点的影响。为此，我们提出了一种新的动态图连续学习框架，称为基于凝缩-拼接的连续学习（CCC）。具体而言，CCC首先将历史图快照凝缩为紧凑的语义表示，同时旨在保持原始标签分布和拓扑属性。然后，它选择性地将这些历史嵌入与当前图表示拼接。此外，我们通过量化结构更新导致现有节点预测性能退化来改进遗忘度量（FM），以更好地适应动态图场景。CCC在四个现实世界数据集上的广泛实验中表现出优于现有最先进基线的性能。
英文摘要：
Dynamic graphs are prevalent in real-world scenarios, where continuous structural changes induce catastrophic forgetting in graph neural networks (GNNs). While continual learning has been extended to dynamic graphs, existing methods overlook the effects of topological changes on existing nodes. To address it, we propose a novel framework for continual learning on dynamic graphs, named Condensation-Concatenation-based Continual Learning (CCC). Specifically, CCC first condenses historical graph snapshots into compact semantic representations while aiming to preserve the original label distribution and topological properties. Then it concatenates these historical embeddings with current graph representations selectively. Moreover, we refine the forgetting measure (FM) to better adapt to dynamic graph scenarios by quantifying the predictive performance degradation of existing nodes caused by structural updates. CCC demonstrates superior performance over state-of-the-art baselines across four real-world datasets in extensive experiments.
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。
