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 2202.11245cs.SIcs.LG
收藏

基于边解纠缠的节点分类算法研究

Exploring Edge Disentanglement for Node Classification

The Pennsylvania State University(宾夕法尼亚州立大学)

Tianxiang Zhao, Xiang Zhang, Suhang Wang

摘要:

现实世界图中的边通常由各种因素形成,并且具有不同的关系语义。例如,社交网络中的连接可以表示友谊,同事或住在同一个社区。然而,由于数据汇集和图形形成过程,这些潜在因素通常被隐藏在仅仅边缘存在的后面。尽管这些年来图学习发展迅速,但大多数模型都采用整体方法,并将所有边视为平等。理清边缘的一个主要困难是缺乏明确的监督。在这项工作中,仔细检查的边缘模式,我们提出了三个算法和设计三个相应的借口任务,以指导自动边缘解开。具体地说,这些自我监督的任务是强制执行设计的边缘解纠缠模块与下游节点分类任务,以鼓励自动边缘解纠缠。解纠缠模块的通道预期捕获可区分的关系和邻域交互,并且将它们的输出聚合为节点表示。所提出的DisGNN很容易与各种神经架构相结合,我们在$6$真实世界的数据集上进行了实验。实验结果表明,它可以实现显着的性能增益。

英文摘要:

Edges in real-world graphs are typically formed by a variety of factors and carry diverse relation semantics. For example, connections in a social network could indicate friendship, being colleagues, or living in the same neighborhood. However, these latent factors are usually concealed behind mere edge existence due to the data collection and graph formation processes. Despite rapid developments in graph learning over these years, most models take a holistic approach and treat all edges as equal. One major difficulty in disentangling edges is the lack of explicit supervisions. In this work, with close examination of edge patterns, we propose three heuristics and design three corresponding pretext tasks to guide the automatic edge disentanglement. Concretely, these self-supervision tasks are enforced on a designed edge disentanglement module to be trained jointly with the downstream node classification task to encourage automatic edge disentanglement. Channels of the disentanglement module are expected to capture distinguishable relations and neighborhood interactions, and outputs from them are aggregated as node representations. The proposed DisGNN is easy to be incorporated with various neural architectures, and we conduct experiments on $6$ real-world datasets. Empirical results show that it can achieve significant performance gains.

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。

↑