About: ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction
Creator	Wang, Hao Liu, Qi Chen, Enhong Hao, Zhongkai Hu, Zheyuan Huang, Zhenya Lee, Cheekong Lu, Chengqiang
Source	ArXiv
abstract	Molecular property prediction (e.g., energy) is an essential problem in chemistry and biology. Unfortunately, many supervised learning methods usually suffer from the problem of scarce labeled molecules in the chemical space, where such property labels are generally obtained by Density Functional Theory (DFT) calculation which is extremely computational costly. An effective solution is to incorporate the unlabeled molecules in a semi-supervised fashion. However, learning semi-supervised representation for large amounts of molecules is challenging, including the joint representation issue of both molecular essence and structure, the conflict between representation and property leaning. Here we propose a novel framework called Active Semi-supervised Graph Neural Network (ASGN) by incorporating both labeled and unlabeled molecules. Specifically, ASGN adopts a teacher-student framework. In the teacher model, we propose a novel semi-supervised learning method to learn general representation that jointly exploits information from molecular structure and molecular distribution. Then in the student model, we target at property prediction task to deal with the learning loss conflict. At last, we proposed a novel active learning strategy in terms of molecular diversities to select informative data during the whole framework learning. We conduct extensive experiments on several public datasets. Experimental results show the remarkable performance of our ASGN framework.
has issue date	2020-07-07(xsd:dateTime)
bibo:doi	10.1145/3394486.3403117
has license	arxiv
sha1sum (hex)	8b229216a36507730f9911433effab08c700195a
schema:url	https://doi.org/10.1145/3394486.3403117
resource representing a document's title	ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction
resource representing a document's body	covid:8b229216a36507730f9911433effab08c700195a#body_text
is schema:about of	named entity 'problem' named entity 'model' named entity 'prediction' named entity 'Molecular property' named entity 'solution' named entity 'Here' named entity 'incorporate' named entity 'large' named entity 'calculation' named entity 'structure' named entity 'learning' named entity 'learning' named entity 'Molecular Property' named entity 'Prediction' named entity 'essence' named entity 'biology' named entity 'generally' named entity 'molecular structure' named entity 'However' named entity 'problem' named entity 'labeled' named entity 'extensive' named entity 'labels' named entity 'conduct' named entity 'representation' named entity 'molecular structure' named entity 'Semi-supervised' named entity 'Neural Network' named entity 'Molecular Property' named entity 'Machine Learning Methods' named entity 'semi-supervised' named entity 'HOMO' named entity 'molecule' named entity 'molecule' named entity 'DFT' named entity 'cross-entropy' named entity 'algorithm' named entity 'training set' named entity 'molecule' named entity 'molecule' named entity 'experimental results' named entity 'posterior distribution' named entity 'representation learning' named entity 'active learning' named entity 'weight transfer' named entity 'representation learning' named entity 'Semi-supervised learning' named entity 'molecule' named entity 'unsupervised learning' named entity 'semi-supervised learning' named entity 'graph embedding' named entity 'DFT' named entity 'message passing' named entity 'neural network' named entity 'molecular graph' named entity 'ladder network' named entity 'Active Learning' named entity 'MAE' named entity 'message passing' named entity 'passive learning' named entity 'Active learning' named entity 'MAE' named entity 'loss function' named entity 'weight transfer' named entity 'semi-supervised learning' named entity 'cross-entropy' named entity 'Semi-supervised' named entity 'G i' named entity 'Representation learning' named entity 'time is time' named entity 'chemical space' named entity 'multi-layer perceptron' named entity 'message passing' named entity 'SSL' named entity 'optimal transport problem' named entity 'semi-supervised learning' named entity 'semi-supervised learning' named entity 'traditional machine learning'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software