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 2106.04113cs.LG
收藏

具有局部和全局结构的自监督图级表示学习

Self-supervised Graph-level Representation Learning with Local and Global Structure

Shanghai Jiao Tong University(上海交通大学);National Research Council Canada(加拿大国家研究委员会);Mila - Quebec AI Institute(米拉-魁北克人工智能研究所);HEC Montréal(蒙特利尔高等商学院)

Minghao Xu, Hang Wang, Bingbing Ni, Hongyu Guo, Jian Tang

摘要:

本文研究了无监督/自监督的全图表示学习,它在药物和材料发现中的分子性质预测等许多任务中至关重要。现有的方法主要集中在保持不同图实例之间的局部相似性结构,而不能发现整个数据集的全局语义结构。在本文中,我们提出了一个统一的框架称为局部实例和全局语义学习(GraphLoG)的自监督全图表示学习。具体地说,除了保留局部相似性之外,GraphLoG还引入了分层原型来捕获全局语义聚类。一个有效的在线期望最大化(EM)算法进一步开发学习模型。我们通过在大量未标记的图上进行预训练,然后对下游任务进行微调来评估GraphLoG。在化学和生物基准数据集上的大量实验证明了该方法的有效性。

英文摘要:

This paper studies unsupervised/self-supervised whole-graph representation learning, which is critical in many tasks such as molecule properties prediction in drug and material discovery. Existing methods mainly focus on preserving the local similarity structure between different graph instances but fail to discover the global semantic structure of the entire data set. In this paper, we propose a unified framework called Local-instance and Global-semantic Learning (GraphLoG) for self-supervised whole-graph representation learning. Specifically, besides preserving the local similarities, GraphLoG introduces the hierarchical prototypes to capture the global semantic clusters. An efficient online expectation-maximization (EM) algorithm is further developed for learning the model. We evaluate GraphLoG by pre-training it on massive unlabeled graphs followed by fine-tuning on downstream tasks. Extensive experiments on both chemical and biological benchmark data sets demonstrate the effectiveness of the proposed approach.

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。

↑