arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.05034cs.LGcs.AI
收藏

SLAPS:自我监督改善图神经网络的结构学习

SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks

University of British Columbia(不列颠哥伦比亚大学);Borealis AI;Google Research(Google研究院)

Bahare Fatemi, Layla El Asri, Seyed Mehran Kazemi

摘要:

当提供图结构时,图神经网络(GNN)工作良好。然而,这种结构在实际应用中可能并不总是可用的。这个问题的一个解决方案是推断特定于任务的潜在结构,然后将GNN应用于推断的图。不幸的是,可能的图结构的空间随着节点的数量超指数增长,因此特定于任务的监督可能不足以学习结构和GNN参数。在这项工作中,我们提出了具有自我监督的邻接和GNN参数的同时学习,或SLAPS,这是一种通过自我监督为推断图结构提供更多监督的方法。一项全面的实验研究表明,SLAPS可扩展到具有数十万个节点的大型图形,并且在已建立的基准上学习特定于任务的图形结构的几种模型中表现出色。

英文摘要:

Graph neural networks (GNNs) work well when the graph structure is provided. However, this structure may not always be available in real-world applications. One solution to this problem is to infer a task-specific latent structure and then apply a GNN to the inferred graph. Unfortunately, the space of possible graph structures grows super-exponentially with the number of nodes and so the task-specific supervision may be insufficient for learning both the structure and the GNN parameters. In this work, we propose the Simultaneous Learning of Adjacency and GNN Parameters with Self-supervision, or SLAPS, a method that provides more supervision for inferring a graph structure through self-supervision. A comprehensive experimental study demonstrates that SLAPS scales to large graphs with hundreds of thousands of nodes and outperforms several models that have been proposed to learn a task-specific graph structure on established benchmarks.

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。

↑