arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.02462cs.SIcs.AI
收藏

对动力学GNN中记忆失效问题的再思考

Rethinking The Memory Staleness Problem In Dynamics GNN

Technion - IIT(以色列理工学院)

Mor Ventura, Hadas Ben Atya, Dekel Brav

摘要:

陈旧性问题是处理动态数据时的一个众所周知的问题,这是由于长时间没有事件。由于节点的内存仅在节点参与事件时更新,因此其内存变得陈旧。通常,它指的是缺乏事件,例如社交帐户的临时停用。为了克服内存老化问题,除了从节点内存中聚合信息外,还从节点邻居内存中聚合信息。受此启发,我们设计了一个更新的嵌入模块,除了节点邻居之外,还插入了最相似的节点。我们的方法取得了类似的结果TGN,略有改进。这可能表明,在微调我们的超参数(特别是时间阈值)并使用可学习的相似性度量之后,可能会有所改进。

英文摘要:

The staleness problem is a well-known problem when working with dynamic data, due to the absence of events for a long time. Since the memory of the node is updated only when the node is involved in an event, its memory becomes stale. Usually, it refers to a lack of events such as a temporal deactivation of a social account. To overcome the memory staleness problem aggregate information from the nodes neighbors memory in addition to the nodes memory. Inspired by that, we design an updated embedding module that inserts the most similar node in addition to the nodes neighbors. Our method achieved similar results to the TGN, with a slight improvement. This could indicate a potential improvement after fine-tuning our hyper-parameters, especially the time threshold, and using a learnable similarity metric.

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。

↑