Motif-Driven Contrastive Learning of Graph Representations

by   Shichang Zhang, et al.

Graph motifs are significant subgraph patterns occurring frequently in graphs, and they play important roles in representing the whole graph characteristics. For example, in chemical domain, functional groups are motifs that can determine molecule properties. Mining and utilizing motifs, however, is a non-trivial task for large graph datasets. Traditional motif discovery approaches rely on exact counting or statistical estimation, which are hard to scale for large datasets with continuous and high-dimension features. In light of the significance and challenges of motif mining, we propose MICRO-Graph: a framework for MotIf-driven Contrastive leaRning Of Graph representations to: 1) pre-train Graph Neural Net-works (GNNs) in a self-supervised manner to automatically extract motifs from large graph datasets; 2) leverage learned motifs to guide the contrastive learning of graph representations, which further benefit various downstream tasks. Specifically, given a graph dataset, a motif learner cluster similar and significant subgraphs into corresponding motif slots. Based on the learned motifs, a motif-guided subgraph segmenter is trained to generate more informative subgraphs, which are used to conduct graph-to-subgraph contrastive learning of GNNs. By pre-training on ogbg-molhiv molecule dataset with our proposed MICRO-Graph, the pre-trained GNN model can enhance various chemical property prediction down-stream tasks with scarce label by 2.0 self-supervised learning baselines.



page 19

page 20


Motif-based Graph Self-Supervised Learning forMolecular Property Prediction

Predicting molecular properties with data-driven methods has drawn much ...

Graph Self-supervised Learning with Accurate Discrepancy Learning

Self-supervised learning of graph neural networks (GNNs) aims to learn a...

Adversarial Graph Augmentation to Improve Graph Contrastive Learning

Self-supervised learning of graph neural networks (GNN) is in great need...

Neural Graph Matching for Pre-training Graph Neural Networks

Recently, graph neural networks (GNNs) have been shown powerful capacity...

Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracing

The goal of Knowledge Tracing (KT) is to estimate how well students have...

Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming

Graph representation learning (GRL) is critical for graph-structured dat...

Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning

Recently, heterogeneous Graph Neural Networks (GNNs) have become a de fa...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.