arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.09262cs.LG
收藏

动态图中感知信息子图的掩码自编码器

Informative Subgraphs Aware Masked Auto-Encoder in Dynamic Graphs

Hangzhou Dianzi University(杭州电子科技大学);Tianjin University(天津大学)

Pengfe Jiao, Xinxun Zhang, Mengzhou Gao, Tianpeng Li, Zhidong Zhao

AI总结:

针对动态图MAE研究匮乏、随机掩码易丢失演化关键时空信息的问题,提出DyGIS模型,通过约束概率生成模型获取信息子图作为DGMAE输入,在11个数据集多任务上达SOTA性能。

摘要:

生成式自监督学习(SSL),尤其是掩码自编码器(MAE),已在图机器学习领域取得巨大成功并引发大量研究兴趣。然而,MAE在动态图中的研究仍然匮乏。这一差距主要源于动态图不仅具备拓扑结构信息,还包含时间演化依赖关系。将大多数MAE方法采用的随机掩码策略应用于动态图时,会移除引导动态图演化的关键子图,导致节点表示中关键时空信息的丢失。为填补这一空白,本文提出了一种新型动态图中感知信息子图的掩码自编码器,名为DyGIS。具体而言,我们引入了一个约束概率生成模型来生成引导动态图演化的信息子图,成功缓解了动态演化子图缺失的问题。DyGIS识别出的信息子图将作为动态图掩码自编码器(DGMAE)的输入,有效保障了动态图内演化时空信息的完整性。在11个数据集上的大量实验表明,DyGIS在多项任务上取得了当前最优(state-of-the-art)性能。

英文摘要:

Generative self-supervised learning (SSL), especially masked autoencoders (MAE), has greatly succeeded and garnered substantial research interest in graph machine learning. However, the research of MAE in dynamic graphs is still scant. This gap is primarily due to the dynamic graph not only possessing topological structure information but also encapsulating temporal evolution dependency. Applying a random masking strategy which most MAE methods adopt to dynamic graphs will remove the crucial subgraph that guides the evolution of dynamic graphs, resulting in the loss of crucial spatio-temporal information in node representations. To bridge this gap, in this paper, we propose a novel Informative Subgraphs Aware Masked Auto-Encoder in Dynamic Graph, namely DyGIS. Specifically, we introduce a constrained probabilistic generative model to generate informative subgraphs that guide the evolution of dynamic graphs, successfully alleviating the issue of missing dynamic evolution subgraphs. The informative subgraph identified by DyGIS will serve as the input of dynamic graph masked autoencoder (DGMAE), effectively ensuring the integrity of the evolutionary spatio-temporal information within dynamic graphs. Extensive experiments on eleven datasets demonstrate that DyGIS achieves state-of-the-art performance across multiple tasks.

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。

↑