Inferring Directed Graphs for Networks from Corrupt Data-Streams

Venkat Ram Subramanian; Andrew Lamperski; Murti V. Salapaka

doi:10.1109/CDC.2018.8619472

Inferring Directed Graphs for Networks from Corrupt Data-Streams

Venkat Ram Subramanian, Andrew Lamperski, Murti V. Salapaka

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

The structure of a complex networked system can be modeled as a graph with nodes representing the agents and the links describing a notion of dynamic coupling between them. Data-driven methods to identify such influence pathways is central to many application domains. However, such dynamically related data-streams originating at different sources are prone to corruption caused by asynchronous time-stamps, packet drops and noise. In this article, we provide a tight characterization of the connectivity structure of the agents that can be constructed based solely on measured data streams that are corrupted. A necessary and sufficient condition that delineates the effects of corruption on a set of nodes is obtained. Here, the generative system that yields the data admits nonlinear dynamic influences between agents and can involve feedback loops. Directed information based concepts are utilized in conjunction with tools from graphical models theory to arrive at the results.

Original language	English (US)
Title of host publication	2018 IEEE Conference on Decision and Control, CDC 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4493-4498
Number of pages	6
ISBN (Electronic)	9781538613955
DOIs	https://doi.org/10.1109/CDC.2018.8619472
State	Published - Jul 2 2018
Event	57th IEEE Conference on Decision and Control, CDC 2018 - Miami, United States Duration: Dec 17 2018 → Dec 19 2018

Publication series

Name	Proceedings of the IEEE Conference on Decision and Control
Volume	2018-December
ISSN (Print)	0743-1546
ISSN (Electronic)	2576-2370

Conference

Conference	57th IEEE Conference on Decision and Control, CDC 2018
Country/Territory	United States
City	Miami
Period	12/17/18 → 12/19/18

Bibliographical note

Funding Information:
∗Work supported in part by NSF CMMI 1727096. The authors are with the Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455, USA.subra148@umn.edu, alampers@umn.edu, murtis@umn.edu

Funding Information:
Work supported in part by NSF CMMI 1727096.

Publisher Copyright:
© 2018 IEEE.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access

10.1109/CDC.2018.8619472

OpenUrl availability

Full text

Cite this

Subramanian, V. R., Lamperski, A., & Salapaka, M. V. (2018). Inferring Directed Graphs for Networks from Corrupt Data-Streams. In 2018 IEEE Conference on Decision and Control, CDC 2018 (pp. 4493-4498). Article 8619472 (Proceedings of the IEEE Conference on Decision and Control; Vol. 2018-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CDC.2018.8619472

Inferring Directed Graphs for Networks from Corrupt Data-Streams. / Subramanian, Venkat Ram; Lamperski, Andrew ; Salapaka, Murti V.
2018 IEEE Conference on Decision and Control, CDC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 4493-4498 8619472 (Proceedings of the IEEE Conference on Decision and Control; Vol. 2018-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Subramanian, VR, Lamperski, A & Salapaka, MV 2018, Inferring Directed Graphs for Networks from Corrupt Data-Streams. in 2018 IEEE Conference on Decision and Control, CDC 2018., 8619472, Proceedings of the IEEE Conference on Decision and Control, vol. 2018-December, Institute of Electrical and Electronics Engineers Inc., pp. 4493-4498, 57th IEEE Conference on Decision and Control, CDC 2018, Miami, United States, 12/17/18. https://doi.org/10.1109/CDC.2018.8619472

@inproceedings{348b8688c0d949dc831c40fe6f5a5c0a,

title = "Inferring Directed Graphs for Networks from Corrupt Data-Streams",

abstract = "The structure of a complex networked system can be modeled as a graph with nodes representing the agents and the links describing a notion of dynamic coupling between them. Data-driven methods to identify such influence pathways is central to many application domains. However, such dynamically related data-streams originating at different sources are prone to corruption caused by asynchronous time-stamps, packet drops and noise. In this article, we provide a tight characterization of the connectivity structure of the agents that can be constructed based solely on measured data streams that are corrupted. A necessary and sufficient condition that delineates the effects of corruption on a set of nodes is obtained. Here, the generative system that yields the data admits nonlinear dynamic influences between agents and can involve feedback loops. Directed information based concepts are utilized in conjunction with tools from graphical models theory to arrive at the results.",

author = "Subramanian, {Venkat Ram} and Andrew Lamperski and Salapaka, {Murti V.}",

note = "Funding Information: ∗Work supported in part by NSF CMMI 1727096. The authors are with the Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455, USA.subra148@umn.edu, alampers@umn.edu, murtis@umn.edu Funding Information: Work supported in part by NSF CMMI 1727096. Publisher Copyright: {\textcopyright} 2018 IEEE.; 57th IEEE Conference on Decision and Control, CDC 2018 ; Conference date: 17-12-2018 Through 19-12-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/CDC.2018.8619472",

language = "English (US)",

series = "Proceedings of the IEEE Conference on Decision and Control",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4493--4498",

booktitle = "2018 IEEE Conference on Decision and Control, CDC 2018",

}

TY - GEN

T1 - Inferring Directed Graphs for Networks from Corrupt Data-Streams

AU - Subramanian, Venkat Ram

AU - Lamperski, Andrew

AU - Salapaka, Murti V.

N1 - Funding Information: ∗Work supported in part by NSF CMMI 1727096. The authors are with the Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455, USA.subra148@umn.edu, alampers@umn.edu, murtis@umn.edu Funding Information: Work supported in part by NSF CMMI 1727096. Publisher Copyright: © 2018 IEEE.

PY - 2018/7/2

Y1 - 2018/7/2

N2 - The structure of a complex networked system can be modeled as a graph with nodes representing the agents and the links describing a notion of dynamic coupling between them. Data-driven methods to identify such influence pathways is central to many application domains. However, such dynamically related data-streams originating at different sources are prone to corruption caused by asynchronous time-stamps, packet drops and noise. In this article, we provide a tight characterization of the connectivity structure of the agents that can be constructed based solely on measured data streams that are corrupted. A necessary and sufficient condition that delineates the effects of corruption on a set of nodes is obtained. Here, the generative system that yields the data admits nonlinear dynamic influences between agents and can involve feedback loops. Directed information based concepts are utilized in conjunction with tools from graphical models theory to arrive at the results.

AB - The structure of a complex networked system can be modeled as a graph with nodes representing the agents and the links describing a notion of dynamic coupling between them. Data-driven methods to identify such influence pathways is central to many application domains. However, such dynamically related data-streams originating at different sources are prone to corruption caused by asynchronous time-stamps, packet drops and noise. In this article, we provide a tight characterization of the connectivity structure of the agents that can be constructed based solely on measured data streams that are corrupted. A necessary and sufficient condition that delineates the effects of corruption on a set of nodes is obtained. Here, the generative system that yields the data admits nonlinear dynamic influences between agents and can involve feedback loops. Directed information based concepts are utilized in conjunction with tools from graphical models theory to arrive at the results.

UR - http://www.scopus.com/inward/record.url?scp=85062183386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062183386&partnerID=8YFLogxK

U2 - 10.1109/CDC.2018.8619472

DO - 10.1109/CDC.2018.8619472

M3 - Conference contribution

AN - SCOPUS:85062183386

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 4493

EP - 4498

BT - 2018 IEEE Conference on Decision and Control, CDC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 57th IEEE Conference on Decision and Control, CDC 2018

Y2 - 17 December 2018 through 19 December 2018

ER -

Inferring Directed Graphs for Networks from Corrupt Data-Streams

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this