Filters








10,427 Hits in 5.2 sec

Structure motif-centric learning framework for inorganic crystalline systems

Huta R Banjade, Sandro Hauri, Shanshan Zhang, Francesco Ricci, Weiyi Gong, Geoffroy Hautier, Slobodan Vucetic, Qimin Yan
2021 Science Advances  
To demonstrate the use of structure motif information, a motif-centric learning framework is created by combining motif information with the atom-based graph neural networks to form an atom-motif dual  ...  graph network (AMDNet), which is more accurate in predicting the electronic structures of metal oxides such as bandgaps.  ...  use in graph-based neural networks for various downstream tasks.  ... 
doi:10.1126/sciadv.abf1754 pmid:33883136 pmcid:PMC8059928 fatcat:x3h772idqvhmjmo4xfaq6rcr44

Structure motif centric learning framework for inorganic crystalline systems [article]

Huta R. Banjade, Sandro Hauri, Shanshan Zhang, Francesco Ricci, Geoffroy Hautier, Slobodan Vucetic, Qimin Yan
2020 arXiv   pre-print
graph neural networks to form an atom-motif dual graph network (AMDNet).  ...  Taking advantage of node and edge information on both atomic and motif level, the AMDNet is more accurate than an atom graph network in predicting electronic structure related material properties of metal  ...  In this work, to enable a learning architecture that synthesize both atom-level and motif-level graph representation of materials, we propose that atom-motif dual graph networks can be constructed to enhance  ... 
arXiv:2007.04145v1 fatcat:2gxto5p5tzfg5br7hadpkvmvna

motif2vec: Motif Aware Node Representation Learning for Heterogeneous Networks [article]

Manoj Reddy Dareddy, Mahashweta Das, Hao Yang
2019 arXiv   pre-print
Specifically, we leverage higher-order, recurring, and statistically significant network connectivity patterns in the form of motifs to transform the original graph to motif graph(s), conduct biased random  ...  Supervised machine learning tasks in networks such as node classification and link prediction require us to perform feature engineering that is known and agreed to be the key to success in applied machine  ...  Such a random walk combined with skip-gram based embedding method learns feature representations f (u) for node u in a homogeneous graph G = {V G , E G } that predicts node u s context neighborhood N (  ... 
arXiv:1908.08227v1 fatcat:v2rz4tieyzh4pkr6wajqdfunfq

Motif-Aware Adversarial Graph Representation Learning

Ming Zhao, Yinglong Zhang, Xuewen Xia, Xing Xu
2022 IEEE Access  
In this paper, for undirected graphs, we present a novel Motif-Aware Generative Adversarial Network (MotifGAN) model to learn graph representation based on a re-weighted graph, which unifies both the Motif  ...  Graph representation learning has been extensively studied in recent years. It has been proven effective in network analysis and mining tasks such as node classification and link prediction.  ...  METHODS BASED ON NEURAL NETWORK These methods are graph representation learning models based on neural network.  ... 
doi:10.1109/access.2022.3144233 fatcat:lsbfu7ov2rakhhqwlpad6lvmw4

Capturing High-order Structures on Motif-based Graph Nerual Networks [article]

Kejia Zhang
2022 arXiv   pre-print
Graph Nerual Networks (GNNs) are effective models in graph embedding.  ...  To address these challenges, we propose a new framework that leverages network motifs to learn deep features of the network from low-level embeddings under the assumption of network homogeneity and transitivity  ...  Vector-based machine learning models can use network embeddings to perform downstream graph analysis tasks such as node classification, link prediction, etc.  ... 
arXiv:2205.00867v2 fatcat:q2gj6glk7rcmjluarrkwn3nh7u

OFFER: A Motif Dimensional Framework for Network Representation Learning

Shuo Yu, Feng Xia, Jin Xu, Zhikui Chen, Ivan Lee
2020 Proceedings of the 29th ACM International Conference on Information & Knowledge Management  
By evaluating the performance of OFFER, both link prediction results and clustering results demonstrate that the graph representation learning algorithms enhanced with OFFER consistently outperform the  ...  In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined.  ...  ACKNOWLEDGMENTS The authors would like to thank Kaiyuan Zhang and Wenya Li for their support and help in the experiment.  ... 
doi:10.1145/3340531.3417446 dblp:conf/cikm/Yu0XCL20 fatcat:zbfmgyiqube7hemrnilikpntr4

OFFER: A Motif Dimensional Framework for Network Representation Learning [article]

Shuo Yu, Feng Xia, Jin Xu, Zhikui Chen, Ivan Lee
2020 arXiv   pre-print
By evaluating the performance of OFFER, both link prediction results and clustering results demonstrate that the graph representation learning algorithms enhanced with OFFER consistently outperform the  ...  In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined.  ...  As an example, for the network representation learning algorithm based on the transition probability matrix P, OFFER refine the learning process in network representation by using MED.  ... 
arXiv:2008.12010v1 fatcat:qgswpwk4mbfybeifaszejil2su

Using Graph Convolutional Neural Networks to Learn a Representation for Glycans [article]

Rebekka Burkholz, John Quackenbush, Daniel Bojar
2021 bioRxiv   pre-print
SweetNet is a graph convolutional neural network model that uses graph representation learning to facilitate a computational understanding of glycobiology.  ...  More importantly, we show that glycan representations, learned by SweetNet, are predictive of organismal phenotypic and environmental properties.  ...  We trained several machine learning models (random forest, K-nearest neighbor), deep learning models such as the glycan-based language model SweetTalk, and graph convolutional neural networks with different  ... 
doi:10.1101/2021.03.01.433491 fatcat:r4gxz2ifgfca3blqd4gnkprffe

Higher-order Network Representation Learning

Ryan A. Rossi, Nesreen K. Ahmed, Eunyee Koh
2018 Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18  
This paper describes a general framework for learning Higher-Order Network Embeddings (HONE) from graph data based on network motifs.  ...  The experimental results demonstrate the effectiveness of learning higher-order network representations.  ...  For each method, we learn embeddings using the remaining graph. Using the embeddings from each method, we then learn a model to predict whether a given edge in the test set exists in E or not.  ... 
doi:10.1145/3184558.3186900 dblp:conf/www/RossiAK18 fatcat:zav4qhlmv5debjvovpbofkpbom

Motif-based Graph Self-Supervised Learning for Molecular Property Prediction [article]

Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu, Chee-Kong Lee
2021 arXiv   pre-print
Particularly, Graph Neural Networks (GNNs) have demonstrated remarkable success in various molecular generation and prediction tasks.  ...  To bridge this gap, we propose Motif-based Graph Self-supervised Learning (MGSSL) by introducing a novel self-supervised motif generation framework for GNNs.  ...  Motif-based Graph Self-supervised Learning In this section, we introduce the framework of motif-based graph self-supervised learning ( Figure 1 ).  ... 
arXiv:2110.00987v2 fatcat:z4ul64xdf5balblecfldnyh7cm

Motif Graph Neural Network [article]

Xuexin Chen, Ruichu Cai, Yuan Fang, Min Wu, Zijian Li, Zhifeng Hao
2022 arXiv   pre-print
These applications can often be cast into standard graph learning tasks, in which a crucial step is to learn low-dimensional graph representations.  ...  Graph neural networks (GNNs) are currently the most popular model in graph embedding approaches.  ...  These applications can often be cast into standard graph learning tasks such as node classification, link prediction, and graph classification, in which a crucial step is to learn lowdimensional graph  ... 
arXiv:2112.14900v2 fatcat:62hynj2qkzeyfhxoztkjhsoimy

Graph-based Molecular Representation Learning [article]

Zhichun Guo, Bozhao Nan, Yijun Tian, Olaf Wiest, Chuxu Zhang, Nitesh V. Chawla
2022 arXiv   pre-print
Recently, MRL has achieved considerable progress, especially in deep molecular graph learning-based methods.  ...  In this survey, we systematically review these graph-based molecular representation techniques. Specifically, we first introduce the data and features of the 2D and 3D graph molecular datasets.  ...  Figure 1 : 1 Figure 1: Overview of graph-based molecular representation learning: (a) Two molecular graphs; (b) The general learning process of graph neural networks; (c) Four methods proposed for graph-based  ... 
arXiv:2207.04869v1 fatcat:eweobqwm55ahdnj2n2umdfdexa

MODEL: Motif-Based Deep Feature Learning for Link Prediction

Lei Wang, Jing Ren, Bo Xu, Jianxin Li, Wei Luo, Feng Xia
2020 IEEE Transactions on Computational Social Systems  
Link prediction plays an important role in network analysis and applications.  ...  In this paper, we propose a novel embedding algorithm that incorporates network motifs to capture higher-order structures in the network.  ...  HONE [9] defines the problem of higher-order network representation learning based on network motifs.  ... 
doi:10.1109/tcss.2019.2962819 fatcat:e2t5pzsu5zayhlawv5fe7j3lie

Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs [article]

Xing Li, Wei Wei, Xiangnan Feng, Xue Liu, Zhiming Zheng
2020 arXiv   pre-print
The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node  ...  However, most of the existing approaches start from the binary relationship (i.e., edges) in the graph and have not leveraged the higher order local structure (i.e., motifs) of the graph.  ...  Thus, representation learning has played a key role in graph machine learning.  ... 
arXiv:2007.15838v1 fatcat:2pnrfxcw5bda5dhaxnxlf4ozv4

RNA Secondary Structure Representation Network for RNA-proteins Binding Prediction

Ziyi Liu, Fulin Luo, Bo Du
2021 AAAI Conference on Artificial Intelligence  
Several deep learning methods, especially the model based on convolutional neural network (CNN), have been used to predict the binding sites.  ...  To effectively extract the structure features of RNA, we propose an RNA secondary structure representation network (RNASSR-Net) based on graph convolutional neural network (GCN) and convolution neural  ...  Acknowledgments The numerical calculations in this paper have been done on the supercomputing system in the Supercomputing Center of Wuhan University.  ... 
dblp:conf/aaai/LiuL021 fatcat:3cqbgexd2va65bfojkjkrwbehi
« Previous Showing results 1 — 15 out of 10,427 results