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 2308.16441cs.AI
收藏

基于多节点中心子图的对比表示学习

Contrastive Representation Learning Based on Multiple Node-centered Subgraphs

Tianjin University(天津大学);Baylor University(贝勒大学)

Dong Li, Wenjun Wang, Minglai Shao, Chen Zhao

AI总结:

针对图表示学习中节点多中心子图特性,提出多节点中心子图对比学习方法,通过最大化同节点不同子图互信息自监督学习节点表示,在多个数据集和下游任务上取得最优结果。

摘要:

作为图结构数据的基本元素,节点已被认为是图表示学习中的主要研究对象。直观上,单个节点在整个图中拥有多个以该节点为中心的子图(例如,社交网络中的一个人基于其不同的关系拥有多个社交圈)。我们在图对比学习的框架下研究这一直觉,并提出一种基于多节点中心子图的对比表示学习方法,以自监督的方式学习图上的节点表示。具体来说,我们精心设计了一系列围绕中心节点的区域性子图。然后,通过对比损失最大化同一节点不同子图之间的互信息。在多个真实世界数据集和不同下游任务上的实验表明,我们的模型取得了最先进的结果。

英文摘要:

As the basic element of graph-structured data, node has been recognized as the main object of study in graph representation learning. A single node intuitively has multiple node-centered subgraphs from the whole graph (e.g., one person in a social network has multiple social circles based on his different relationships). We study this intuition under the framework of graph contrastive learning, and propose a multiple node-centered subgraphs contrastive representation learning method to learn node representation on graphs in a self-supervised way. Specifically, we carefully design a series of node-centered regional subgraphs of the central node. Then, the mutual information between different subgraphs of the same node is maximized by contrastive loss. Experiments on various real-world datasets and different downstream tasks demonstrate that our model has achieved state-of-the-art results.

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。

↑