MOTIF-Driven Contrastive Learning of Graph Representations

Authors

  • Arjun Subramonian University of California, Los Angeles

Keywords:

Knowledge Discovery, Deep Learning, Machine Learning, Data Mining

Abstract

We propose a MOTIF-driven contrastive framework to pretrain a graph neural network in a self-supervised manner so that it can automatically mine motifs from large graph datasets. Our framework achieves state-of-the-art results on various graph-level downstream tasks with few labels, like molecular property prediction.

Downloads

Published

2021-05-18

How to Cite

Subramonian, A. . (2021). MOTIF-Driven Contrastive Learning of Graph Representations. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15980-15981. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17986

Issue

Section

AAAI Undergraduate Consortium