conftrace_

2021 AAAI AAAI 2021

MOTIF-Driven Contrastive Learning of Graph Representations

Abstract

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.

🐣 Hot Topic Early Bird - molecular property prediction

Authors

Arjun Subramonian

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Learning Types > Self-Supervised Learning Deep Learning > Architectures > Graph Neural Networks Deep Learning > Learning Types > Self-Supervised Learning Deep Learning > Learning Types > Contrastive Learning

Keywords

contrastive learning self-supervised learning graph representation molecular property prediction graph neural network motif mining

More from AAAI 2021

All AAAI 2021 papers →

Use of Computer Vision to Develop a Device to Assist Visually Impaired People with Social Distance.

Predictive Agent-Based Modeling of Natural Disasters Using Machine Learning

Investigating Methods of Balancing Inequality and Efficiency in Ride Pooling

Bison Hacks the Yard: Assisting Underrepresented Students Overcome Impostor Syndrome with Augmented Reality and Artificial Intelligence

A Semantic Parsing and Reasoning-Based Approach to Knowledge Base Question Answering

Exploring the Efficacy of Generic Drugs in Treating Cancer