CA-DGCL：通过凝聚和附着实现动态图持续学习

中文摘要 AI 辅助

动态图持续学习（DGCL）是处理动态图中灾难性遗忘的有效方式。然而，现有DGCL方法未充分利用跨图快照的时间信息。为解决这一关键问题，我们提出了一种通过凝聚和附着实现动态图持续学习的新框架（CA-DGCL）。具体而言，CA-DGCL首先将历史图快照高效凝聚为紧凑的语义表示。接着，构建跨时间戳节点链以构造三阶张量，并对该张量应用塔克分解来获取封装历史知识的稳定节点特征。最后，利用这些节点特征生成新节点并附着到当前图以重放过去信息。此外，引入了一种改进的遗忘度量使其更适用于动态图设置。大量实验表明，CA-DGCL在遗忘抑制方面优于基线，并保持了有竞争力的准确率，证明了其对动态图持续学习的有效性。

英文摘要

Dynamic graph continual learning (DGCL) is an effective manner for handling catastrophic forgetting in dynamic graphs. However, existing DGCL methods underutilize temporal information across graph snapshots. To address this critical issue, we propose a novel framework for Dynamic Graph Continual Learning via Condensation and Attachment (CA-DGCL). Specifically, CA-DGCL first condenses historical graph snapshots into compact semantic representations efficiently. Further, a cross-timestamp node chains is built to construct a third-order tensor and Tucker decomposition is applied to this tensor for obtaining stable node features, which encapsulate historical knowledge. Finally, these node features are used to generate new nodes and attached to the current graph for replaying of past information without compromising the new patterns. In addtion, a refined forgetting measure is introduced to make it more suitable for dynamic graph settings. Extensive experiments demonstrate that CA-DGCL outperforms baselines in forgetting suppression as well as maintain competitive accuracy, proving its efficacy for dynamic graph continual learning.

发表机构

• College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）

机构由 AI 辅助整理，请以论文原文为准。