Visual Analytics of Heterogeneous Data Using Hypergraph Learning
Abstract
For real-world learning tasks (e.g., classification), graph-based models are commonly used to fuse the information distributed in diverse data sources, which can be heterogeneous, redundant, and incomplete. Thesemodels represent the relations in different datasets as pairwise links. However, these links cannot deal with high-order relations which connect multiple objects (e.g., in public health datasets, more than two patient groups admitted by the same hospital in 2014). In this article, we propose a visual analytics approach forthe classification on heterogeneous datasets using the hypergraph model. The hypergraph is an extension to traditional graphs in which a hyperedge connects multiple vertices instead of just two. We model various high-order relations in heterogeneous datasets as hyperedges and fuse different datasets with a unified hypergraph structure. We use the hypergraph learning algorithm for predicting missing labels in the datasets.To allow users to inject their domain knowledge into the model-learning process, we augment the traditional learning algorithm in a number of ways. In addition, we also propose a set of visualizations which enable the user to construct the hypergraph structure and the parameters of the learning model interactively during the analysis. Here, we demonstrate the capability of our approach via two real-world cases.
- Authors:
-
- Stony Brook Univ., Stony Brook, NY (United States)
- Brookhaven National Lab. (BNL), Upton, NY (United States)
- Publication Date:
- Research Org.:
- Brookhaven National Laboratory (BNL), Upton, NY (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (SC-21)
- OSTI Identifier:
- 1496572
- Report Number(s):
- BNL-211294-2019-JAAM
Journal ID: ISSN 2157-6904
- Grant/Contract Number:
- SC0012704
- Resource Type:
- Accepted Manuscript
- Journal Name:
- ACM Transactions on Intelligent Systems and Technology
- Additional Journal Information:
- Journal Volume: 10; Journal Issue: 1; Journal ID: ISSN 2157-6904
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; hypergraph learning; data fusion; high-dimensional data
Citation Formats
Xie, Cong, Zhong, Wen, Xu, Wei, and Mueller, Klaus. Visual Analytics of Heterogeneous Data Using Hypergraph Learning. United States: N. p., 2018.
Web. doi:10.1145/3200765.
Xie, Cong, Zhong, Wen, Xu, Wei, & Mueller, Klaus. Visual Analytics of Heterogeneous Data Using Hypergraph Learning. United States. https://doi.org/10.1145/3200765
Xie, Cong, Zhong, Wen, Xu, Wei, and Mueller, Klaus. Sat .
"Visual Analytics of Heterogeneous Data Using Hypergraph Learning". United States. https://doi.org/10.1145/3200765. https://www.osti.gov/servlets/purl/1496572.
@article{osti_1496572,
title = {Visual Analytics of Heterogeneous Data Using Hypergraph Learning},
author = {Xie, Cong and Zhong, Wen and Xu, Wei and Mueller, Klaus},
abstractNote = {For real-world learning tasks (e.g., classification), graph-based models are commonly used to fuse the information distributed in diverse data sources, which can be heterogeneous, redundant, and incomplete. Thesemodels represent the relations in different datasets as pairwise links. However, these links cannot deal with high-order relations which connect multiple objects (e.g., in public health datasets, more than two patient groups admitted by the same hospital in 2014). In this article, we propose a visual analytics approach forthe classification on heterogeneous datasets using the hypergraph model. The hypergraph is an extension to traditional graphs in which a hyperedge connects multiple vertices instead of just two. We model various high-order relations in heterogeneous datasets as hyperedges and fuse different datasets with a unified hypergraph structure. We use the hypergraph learning algorithm for predicting missing labels in the datasets.To allow users to inject their domain knowledge into the model-learning process, we augment the traditional learning algorithm in a number of ways. In addition, we also propose a set of visualizations which enable the user to construct the hypergraph structure and the parameters of the learning model interactively during the analysis. Here, we demonstrate the capability of our approach via two real-world cases.},
doi = {10.1145/3200765},
journal = {ACM Transactions on Intelligent Systems and Technology},
number = 1,
volume = 10,
place = {United States},
year = {Sat Dec 01 00:00:00 EST 2018},
month = {Sat Dec 01 00:00:00 EST 2018}
}
Web of Science
Works referenced in this record:
Bubble Sets: Revealing Set Relations with Isocontours over Existing Visualizations
journal, November 2009
- Collins, C.; Penn, G.; Carpendale, S.
- IEEE Transactions on Visualization and Computer Graphics, Vol. 15, Issue 6
The Data Context Map: Fusing Data and Attributes into a Unified Display
journal, January 2016
- Cheng, Shenghui; Mueller, Klaus
- IEEE Transactions on Visualization and Computer Graphics, Vol. 22, Issue 1
Tag-based social image search with visual-text joint hypergraph learning
conference, January 2011
- Gao, Yue; Wang, Meng; Luan, Huanbo
- Proceedings of the 19th ACM international conference on Multimedia - MM '11
OnSet: A Visualization Technique for Large-scale Binary Set Data
journal, December 2014
- Sadana, Ramik; Major, Timothy; Dove, Alistair
- IEEE Transactions on Visualization and Computer Graphics, Vol. 20, Issue 12
A Utility-Aware Visual Approach for Anonymizing Multi-Attribute Tabular Data
journal, January 2018
- Wang, Xumeng; Chou, Jia-Kai; Chen, Wei
- IEEE Transactions on Visualization and Computer Graphics, Vol. 24, Issue 1
Resource description framework: metadata and its applications
journal, July 2001
- Candan, K. Selçuk; Liu, Huan; Suvarna, Reshma
- ACM SIGKDD Explorations Newsletter, Vol. 3, Issue 1
UpSet: Visualization of Intersecting Sets
journal, December 2014
- Lex, Alexander; Gehlenborg, Nils; Strobelt, Hendrik
- IEEE Transactions on Visualization and Computer Graphics, Vol. 20, Issue 12
Visualization of Heterogeneous Data
journal, November 2007
- Cammarano, Mike; Dong, Xin; Chan, Bryan
- IEEE Transactions on Visualization and Computer Graphics, Vol. 13, Issue 6
Hypergraph spectral learning for multi-label classification
conference, January 2008
- Sun, Liang; Ji, Shuiwang; Ye, Jieping
- Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD 08
Link mining: a survey
journal, December 2005
- Getoor, Lise; Diehl, Christopher P.
- ACM SIGKDD Explorations Newsletter, Vol. 7, Issue 2
News recommendation via hypergraph learning: encapsulation of user behavior and news content
conference, January 2013
- Li, Lei; Li, Tao
- Proceedings of the sixth ACM international conference on Web search and data mining - WSDM '13
Exploring the Possibilities of Embedding Heterogeneous Data Attributes in Familiar Visualizations
journal, January 2017
- Loorak, Mona Hosseinkhani; Perin, Charles; Collins, Christopher
- IEEE Transactions on Visualization and Computer Graphics, Vol. 23, Issue 1
Inductively Generating Euler Diagrams
journal, January 2011
- Stapleton, G.; Rodgers, P.; Howse, J.
- IEEE Transactions on Visualization and Computer Graphics, Vol. 17, Issue 1
Visualizing set concordance with permutation matrices and fan diagrams
journal, December 2007
- Kim, Bohyoung; Lee, Bongshin; Seo, Jinwook
- Interacting with Computers, Vol. 19, Issue 5-6
Hypergraph with sampling for image retrieval
journal, October 2011
- Liu, Qingshan; Huang, Yuchi; Metaxas, Dimitris N.
- Pattern Recognition, Vol. 44, Issue 10-11
Uncertainty-Aware Multidimensional Ensemble Data Visualization and Exploration
journal, September 2015
- Chen, Haidong; Zhang, Song; Chen, Wei
- IEEE Transactions on Visualization and Computer Graphics, Vol. 21, Issue 9
Graph drawing by force-directed placement
journal, November 1991
- Fruchterman, Thomas M. J.; Reingold, Edward M.
- Software: Practice and Experience, Vol. 21, Issue 11
Music recommendation by unified hypergraph: combining social media information and music content
conference, January 2010
- Bu, Jiajun; Tan, Shulong; Chen, Chun
- Proceedings of the international conference on Multimedia - MM '10
KelpFusion: A Hybrid Set Visualization Technique
journal, November 2013
- Meulemans, Wouter; Riche, Nathalie Henry; Speckmann, Bettina
- IEEE Transactions on Visualization and Computer Graphics, Vol. 19, Issue 11
Refinery: Visual Exploration of Large, Heterogeneous Networks through Associative Browsing
journal, June 2015
- Kairam, S.; Riche, N. H.; Drucker, S.
- Computer Graphics Forum, Vol. 34, Issue 3
On the effect of hyperedge weights on hypergraph learning
journal, January 2017
- Huang, Sheng; Elgammal, Ahmed; Yang, Dan
- Image and Vision Computing, Vol. 57
A visual analytical approach for transfer learning in classification
journal, June 2017
- Ma, Yuxin; Xu, Jiayi; Wu, Xiangyang
- Information Sciences, Vol. 390