Log In Sign Up

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

by   Minghao Xu, et al.

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.


Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning

Unsupervised/self-supervised graph representation learning is critical f...

SGR: Self-Supervised Spectral Graph Representation Learning

Representing a graph as a vector is a challenging task; ideally, the rep...

Multi-task Joint Strategies of Self-supervised Representation Learning on Biomedical Networks for Drug Discovery

Self-supervised representation learning (SSL) on biomedical networks pro...

Global-Local Self-Distillation for Visual Representation Learning

The downstream accuracy of self-supervised methods is tightly linked to ...

MolE: a molecular foundation model for drug discovery

Models that accurately predict properties based on chemical structure ar...

Self-Supervised Visual Representation Learning from Hierarchical Grouping

We create a framework for bootstrapping visual representation learning f...

Self-Supervised Representation Learning via Neighborhood-Relational Encoding

In this paper, we propose a novel self-supervised representation learnin...

Code Repositories


Implementation of Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021).

view repo