Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form
D-Scholarship @ Pitt Banner and Links to Homepage

GB-R: A Fast and Effective Gray-Box Reconstruction of Cascade Time-Series.

Song, Hyun Ah and Yang, Fan and Van Panhuis, WG and Sidiropoulos, Nicholas and Faloutsos, Christos and Zadorozhny, Vladimir (2017) GB-R: A Fast and Effective Gray-Box Reconstruction of Cascade Time-Series. In: Data Mining in Biomedical Informatics and Healthcare (DMBIH) Workshop, in conjunction with IEEE International Conference on Data Mining (ICDM’17), 18-21 November 2017, New Orleans, USA.

Abstract

Given some (but not all) monthly totals of people with measles (or counts of product-units sold, or counts of retweets), how can we recover the weekly counts? Requiring smoothness between successive weeks is reasonable - but can we do better, if we have some domain knowledge? For example, we know that measles (flu, count-of-retweets, etc) follow a specific cascade model, like the so-called 'SIS'. The answer is 'yes'. With our proposed GB-R we show how to inject domain knowledge, creating a gray-box model; we show how to set up and efficiently solve the appropriate optimization problem. The desirable properties of our GB-R are: (a) effectiveness, outperforming the best competitors on real, epidemiology data, often by 3x - 25x in reconstruction error; (b) scalability, being linear on the sequence length and (c) interpretability, accurately estimating the parameters of the gray-box model.

Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Conference or Workshop Item (Paper)
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Song, Hyun Ah
Yang, Fanfay23@pitt.eduFAY23
Van Panhuis, WG
Sidiropoulos, Nicholas
Faloutsos, Christos
Zadorozhny, Vladimirviz@pitt.eduviz0000-0001-6420-1926
Date: 2017
Date Type: Publication
Journal or Publication Title: Data Mining in Biomedical Informatics and Healthcare (DMBIH) Workshop, in conjunction with IEEE International Conference on Data Mining (ICDM’17)
Publisher: IEEE
Event Title: Data Mining in Biomedical Informatics and Healthcare (DMBIH) Workshop, in conjunction with IEEE International Conference on Data Mining (ICDM’17)
Event Dates: 18-21 November 2017
Event Type: Workshop
Schools and Programs: School of Computing and Information > Information Science
Refereed: Yes
Related URLs:
Date Deposited: 05 Jul 2018 19:10
Last Modified: 05 Jul 2018 19:10
URI: http://d-scholarship.pitt.edu/id/eprint/34836

Metrics

Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item