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 2107.09787cs.LG
收藏

图的群体对比自监督学习

Group Contrastive Self-Supervised Learning on Graphs

Xidian University(西安电子科技大学);Texas A&M University(得克萨斯农工大学)

Xinyi Xu, Cheng Deng, Yaochen Xie, Shuiwang Ji

摘要:

我们使用对比的方法研究图上的自监督学习。现有方法的一般方案是优化输入图的双视图表示。在许多研究中,一个单一的图级表示计算作为对比的目标之一,捕捉有限的图的特性。我们认为,对比图在多个子空间,使图形编码器捕捉更丰富的特征。为此,我们提出了一个小组对比学习框架在这项工作中。我们的框架将给定的图嵌入到多个子空间中,其中每个表示都提示对图的特定特征进行编码。为了学习多样化和信息丰富的表征,我们制定了原则性的目标,使我们能够捕捉组内空间和空间表征之间的关系。在所提出的框架下,我们进一步开发了一个基于注意力的representor函数来计算捕获给定图的不同子结构的表示。建立在我们的框架,我们扩展到GroupCL和GroupIG,配备了拟议的目标,目前的两种方法。综合的实验结果表明,我们的框架在各种数据集上实现了有希望的性能提升。此外,我们的定性结果表明,从我们的representor生成的功能成功地捕捉各种特定的图的特征。

英文摘要:

We study self-supervised learning on graphs using contrastive methods. A general scheme of prior methods is to optimize two-view representations of input graphs. In many studies, a single graph-level representation is computed as one of the contrastive objectives, capturing limited characteristics of graphs. We argue that contrasting graphs in multiple subspaces enables graph encoders to capture more abundant characteristics. To this end, we propose a group contrastive learning framework in this work. Our framework embeds the given graph into multiple subspaces, of which each representation is prompted to encode specific characteristics of graphs. To learn diverse and informative representations, we develop principled objectives that enable us to capture the relations among both intra-space and inter-space representations in groups. Under the proposed framework, we further develop an attention-based representor function to compute representations that capture different substructures of a given graph. Built upon our framework, we extend two current methods into GroupCL and GroupIG, equipped with the proposed objective. Comprehensive experimental results show our framework achieves a promising boost in performance on a variety of datasets. In addition, our qualitative results show that features generated from our representor successfully capture various specific characteristics of graphs.

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。

↑