← Back to papers
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.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
🧭 Keyword Pioneer — motif mining
🐣 Hot Topic Early Bird — molecular property prediction
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

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
Download PDF

Related papers

Contextual Conditional Reasoning 2021
Attention Beam: An Image Captioning Approach (Student Abstract) 2021
Movie Summarization via Sparse Graph Construction 2021
Text Analysis for Understanding Symptoms of Social Anxiety in Student Veterans 2021
ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs 2021