logo
ResearchBunny Logo
Hierarchical Molecular Graph Self-Supervised Learning for property prediction

Chemistry

Hierarchical Molecular Graph Self-Supervised Learning for property prediction

X. Zang, X. Zhao, et al.

This exciting research introduces HiMol, a pre-training framework that leverages Hierarchical Molecular Graph Neural Networks to decode intricate molecular structures and predict their properties. Conducted by Xuan Zang, Xianbing Zhao, and Buzhou Tang, this work demonstrates remarkable effectiveness in understanding chemical semantics through innovative self-supervised learning techniques.

00:00
00:00
Playback language: English
Abstract
This paper introduces Hierarchical Molecular Graph Self-supervised Learning (HiMol), a pre-training framework for learning molecular representations to predict properties. HiMol uses a Hierarchical Molecular Graph Neural Network (HMGNN) to encode motif structures and extract hierarchical representations. Multi-level Self-supervised Pre-training (MSP) employs generative and predictive tasks as self-supervised signals. Results on classification and regression tasks demonstrate HiMol's effectiveness, and visualizations show its ability to capture chemical semantic information.
Publisher
Communications Chemistry
Published On
Feb 17, 2023
Authors
Xuan Zang, Xianbing Zhao, Buzhou Tang
Tags
Molecular Graph Neural Network
Self-supervised Learning
Hierarchical Representations
Chemical Properties
Generative Tasks
Predictive Tasks
Motif Structures

Related Publications

Explore these studies to deepen your understanding of the subject.

Crystal Twins: Self-Supervised Learning for Crystalline Material Property Prediction
Engineering and Technology

Crystal Twins: Self-Supervised Learning for Crystalline Material Property Prediction

R. Magar, Y. Wang, et al.

Self-supervised learning for human activity recognition using 700,000 person-days of wearable data
Computer Science

Self-supervised learning for human activity recognition using 700,000 person-days of wearable data

H. Yuan, S. Chan, et al.

Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality
Health and Fitness

Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality

H. Yuan, T. Plekhanova, et al.

Self-supervised machine learning for live cell imagery segmentation
Biology

Self-supervised machine learning for live cell imagery segmentation

M. C. Robitaille, J. M. Byers, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny