Towards adaptive spiking label propagation

Kathleen E. Hamilton; Catherine D. Schuman

doi:10.1145/3229884.3229897

Towards adaptive spiking label propagation

Kathleen E. Hamilton, Catherine D. Schuman

Quantum Computational Science

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

4 Scopus citations

Abstract

Graph algorithms are a new class of applications for neuromorphic hardware. Rather than adapting deep learning and standard neural network approaches to a low-precision spiking environment,we use spiking neurons to analyze undirected graphs (e.g., the underlying modular structure). While fully connected spin glass implementations of spiking label propagation have shown promising results on graphs with dense communities, identifying sparse communities remains difficult. This work focuses on steps towards an adaptive spike-based implementations of label propagation, utilizing sparse embeddings and synaptic plasticity. Sparser embeddings reduce the number of inhibitory connections, and synaptic plasticity is used to simultaneously amplify spike responses between neurons in the same community, while impeding spike responses across different communities. We present results on identifying communities in sparse graphs with very small communities.

Original language	English
Title of host publication	ICONS 2018 - Proceedings of International Conference on Neuromorphic Systems 2018
Publisher	Association for Computing Machinery
ISBN (Print)	9781450365444
DOIs	https://doi.org/10.1145/3229884.3229897
State	Published - Jul 23 2018
Event	2018 International Conference on Neuromorphic Systems, ICONS 2018 - Knoxville, United States Duration: Jul 23 2018 → Jul 26 2018

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2018 International Conference on Neuromorphic Systems, ICONS 2018
Country/Territory	United States
City	Knoxville
Period	07/23/18 → 07/26/18

Funding

Research sponsored in part by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the U. S. Department of Energy. ∗This work was supported by the United States Department of Defense and used resources of the Computational Research and Development Programs at Oak Ridge National Laboratory. This manuscript has been authored by UT-Battelle, LLC, under Contract No. DE-AC0500OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for the United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan.

Keywords

Community detection
Graph algorithm
Neuromorphic
Path finding
Spiking neural networks

Access to Document

10.1145/3229884.3229897

Cite this

@inproceedings{cc2c2483c20444528969a6e33776e665,

title = "Towards adaptive spiking label propagation",

abstract = "Graph algorithms are a new class of applications for neuromorphic hardware. Rather than adapting deep learning and standard neural network approaches to a low-precision spiking environment,we use spiking neurons to analyze undirected graphs (e.g., the underlying modular structure). While fully connected spin glass implementations of spiking label propagation have shown promising results on graphs with dense communities, identifying sparse communities remains difficult. This work focuses on steps towards an adaptive spike-based implementations of label propagation, utilizing sparse embeddings and synaptic plasticity. Sparser embeddings reduce the number of inhibitory connections, and synaptic plasticity is used to simultaneously amplify spike responses between neurons in the same community, while impeding spike responses across different communities. We present results on identifying communities in sparse graphs with very small communities.",

keywords = "Community detection, Graph algorithm, Neuromorphic, Path finding, Spiking neural networks",

author = "Hamilton, {Kathleen E.} and Schuman, {Catherine D.}",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 2018 International Conference on Neuromorphic Systems, ICONS 2018 ; Conference date: 23-07-2018 Through 26-07-2018",

year = "2018",

month = jul,

day = "23",

doi = "10.1145/3229884.3229897",

language = "English",

isbn = "9781450365444",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

booktitle = "ICONS 2018 - Proceedings of International Conference on Neuromorphic Systems 2018",

}

Hamilton, KE & Schuman, CD 2018, Towards adaptive spiking label propagation. in ICONS 2018 - Proceedings of International Conference on Neuromorphic Systems 2018. ACM International Conference Proceeding Series, Association for Computing Machinery, 2018 International Conference on Neuromorphic Systems, ICONS 2018, Knoxville, United States, 07/23/18. https://doi.org/10.1145/3229884.3229897

Towards adaptive spiking label propagation. / Hamilton, Kathleen E.; Schuman, Catherine D.
ICONS 2018 - Proceedings of International Conference on Neuromorphic Systems 2018. Association for Computing Machinery, 2018. (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Towards adaptive spiking label propagation

AU - Hamilton, Kathleen E.

AU - Schuman, Catherine D.

PY - 2018/7/23

Y1 - 2018/7/23

N2 - Graph algorithms are a new class of applications for neuromorphic hardware. Rather than adapting deep learning and standard neural network approaches to a low-precision spiking environment,we use spiking neurons to analyze undirected graphs (e.g., the underlying modular structure). While fully connected spin glass implementations of spiking label propagation have shown promising results on graphs with dense communities, identifying sparse communities remains difficult. This work focuses on steps towards an adaptive spike-based implementations of label propagation, utilizing sparse embeddings and synaptic plasticity. Sparser embeddings reduce the number of inhibitory connections, and synaptic plasticity is used to simultaneously amplify spike responses between neurons in the same community, while impeding spike responses across different communities. We present results on identifying communities in sparse graphs with very small communities.

AB - Graph algorithms are a new class of applications for neuromorphic hardware. Rather than adapting deep learning and standard neural network approaches to a low-precision spiking environment,we use spiking neurons to analyze undirected graphs (e.g., the underlying modular structure). While fully connected spin glass implementations of spiking label propagation have shown promising results on graphs with dense communities, identifying sparse communities remains difficult. This work focuses on steps towards an adaptive spike-based implementations of label propagation, utilizing sparse embeddings and synaptic plasticity. Sparser embeddings reduce the number of inhibitory connections, and synaptic plasticity is used to simultaneously amplify spike responses between neurons in the same community, while impeding spike responses across different communities. We present results on identifying communities in sparse graphs with very small communities.

KW - Community detection

KW - Graph algorithm

KW - Neuromorphic

KW - Path finding

KW - Spiking neural networks

UR - http://www.scopus.com/inward/record.url?scp=85051507102&partnerID=8YFLogxK

U2 - 10.1145/3229884.3229897

DO - 10.1145/3229884.3229897

M3 - Conference contribution

AN - SCOPUS:85051507102

SN - 9781450365444

T3 - ACM International Conference Proceeding Series

BT - ICONS 2018 - Proceedings of International Conference on Neuromorphic Systems 2018

PB - Association for Computing Machinery

T2 - 2018 International Conference on Neuromorphic Systems, ICONS 2018

Y2 - 23 July 2018 through 26 July 2018

ER -

Towards adaptive spiking label propagation

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this