Timezone: »

Self-supervised Graph-level Representation Learning with Local and Global Structure
Minghao Xu · Hang Wang · Bingbing Ni · Hongyu Guo · Jian Tang

Thu Jul 22 09:00 PM -- 11:00 PM (PDT) @ Virtual

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.

Author Information

Minghao Xu (Shanghai Jiao Tong University)
Hang Wang (Shanghai Jiao Tong University)
Bingbing Ni (Shanghai Jiao Tong University)
Hongyu Guo (National Research Council Canada)
Jian Tang (HEC Montreal & MILA)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors