The impact of splitting granularity on multi-agent diffusion computing

Xiaocong Fan, Meng Su

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Diffusion geometry offers a fresh perspective on multi-scale information analysis. However, there is still a lack of work on distributed approach to diffusion computing. In this paper, we propose a multi-agent diffusion approach where a massive data set is split into several subsets and each diffusion agent only needs to work with one subset in diffusion computation. We apply it to a large set of human decisionmaking experiences. The result indicates that the multi-agent diffusion approach is beneficial, and the system performance could be affected significantly by the splitting granularity (size of each splitting unit). This study encourages further theoretical investigations on the potential impacts of splitting granularity on the recoverability of the global diffusion map.

Original languageEnglish (US)
Title of host publicationProceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011
Pages216-219
Number of pages4
Volume2
DOIs
StatePublished - 2011
Event2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011 - Lyon, France
Duration: Aug 22 2011Aug 27 2011

Other

Other2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011
CountryFrance
CityLyon
Period8/22/118/27/11

Fingerprint

Information analysis
Set theory
Geometry

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Fan, X., & Su, M. (2011). The impact of splitting granularity on multi-agent diffusion computing. In Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011 (Vol. 2, pp. 216-219). [6040780] https://doi.org/10.1109/WI-IAT.2011.53
Fan, Xiaocong ; Su, Meng. / The impact of splitting granularity on multi-agent diffusion computing. Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011. Vol. 2 2011. pp. 216-219
@inproceedings{c4752d8054e542bc989217273393b14d,
title = "The impact of splitting granularity on multi-agent diffusion computing",
abstract = "Diffusion geometry offers a fresh perspective on multi-scale information analysis. However, there is still a lack of work on distributed approach to diffusion computing. In this paper, we propose a multi-agent diffusion approach where a massive data set is split into several subsets and each diffusion agent only needs to work with one subset in diffusion computation. We apply it to a large set of human decisionmaking experiences. The result indicates that the multi-agent diffusion approach is beneficial, and the system performance could be affected significantly by the splitting granularity (size of each splitting unit). This study encourages further theoretical investigations on the potential impacts of splitting granularity on the recoverability of the global diffusion map.",
author = "Xiaocong Fan and Meng Su",
year = "2011",
doi = "10.1109/WI-IAT.2011.53",
language = "English (US)",
isbn = "9780769545134",
volume = "2",
pages = "216--219",
booktitle = "Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011",

}

Fan, X & Su, M 2011, The impact of splitting granularity on multi-agent diffusion computing. in Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011. vol. 2, 6040780, pp. 216-219, 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011, Lyon, France, 8/22/11. https://doi.org/10.1109/WI-IAT.2011.53

The impact of splitting granularity on multi-agent diffusion computing. / Fan, Xiaocong; Su, Meng.

Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011. Vol. 2 2011. p. 216-219 6040780.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - The impact of splitting granularity on multi-agent diffusion computing

AU - Fan, Xiaocong

AU - Su, Meng

PY - 2011

Y1 - 2011

N2 - Diffusion geometry offers a fresh perspective on multi-scale information analysis. However, there is still a lack of work on distributed approach to diffusion computing. In this paper, we propose a multi-agent diffusion approach where a massive data set is split into several subsets and each diffusion agent only needs to work with one subset in diffusion computation. We apply it to a large set of human decisionmaking experiences. The result indicates that the multi-agent diffusion approach is beneficial, and the system performance could be affected significantly by the splitting granularity (size of each splitting unit). This study encourages further theoretical investigations on the potential impacts of splitting granularity on the recoverability of the global diffusion map.

AB - Diffusion geometry offers a fresh perspective on multi-scale information analysis. However, there is still a lack of work on distributed approach to diffusion computing. In this paper, we propose a multi-agent diffusion approach where a massive data set is split into several subsets and each diffusion agent only needs to work with one subset in diffusion computation. We apply it to a large set of human decisionmaking experiences. The result indicates that the multi-agent diffusion approach is beneficial, and the system performance could be affected significantly by the splitting granularity (size of each splitting unit). This study encourages further theoretical investigations on the potential impacts of splitting granularity on the recoverability of the global diffusion map.

UR - http://www.scopus.com/inward/record.url?scp=80155195225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80155195225&partnerID=8YFLogxK

U2 - 10.1109/WI-IAT.2011.53

DO - 10.1109/WI-IAT.2011.53

M3 - Conference contribution

SN - 9780769545134

VL - 2

SP - 216

EP - 219

BT - Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011

ER -

Fan X, Su M. The impact of splitting granularity on multi-agent diffusion computing. In Proceedings - 2011 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2011. Vol. 2. 2011. p. 216-219. 6040780 https://doi.org/10.1109/WI-IAT.2011.53