Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation

Guojing Cong; Shruti Kulkarni; Seung Hwan Lim; Prasanna Date; Shay Snyder; Maryam Parsa; Dominic Kennedy; Catherine Schuman

doi:10.1109/ICMLA58977.2023.00232

Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation

Guojing Cong, Shruti Kulkarni, Seung Hwan Lim, Prasanna Date, Shay Snyder, Maryam Parsa, Dominic Kennedy, Catherine Schuman

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

5 Scopus citations

Abstract

Graph convolutional networks leverage both graph structures and features on nodes and edges for improved learning performance in comparison with classical machine learning approaches. Spiking neuromorphic computers natively implement network-like computation and have been shown to be successful at implementing graph learning without features. Incorporating graph features brings the challenge of efficient feature representation and balancing the contribution of topology and features in learning. In this work, we present our design of a simulated network of spiking neurons to perform semi-supervised learning on graph data using both the graph structure and the node features. We explore various design choices, present preliminary results, and discuss the opportunities for using neuromorphic computers for this task in the future.

Original language	English
Title of host publication	Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023
Editors	M. Arif Wani, Mihai Boicu, Moamar Sayed-Mouchaweh, Pedro Henriques Abreu, Joao Gama
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1541-1546
Number of pages	6
ISBN (Electronic)	9798350345346
DOIs	https://doi.org/10.1109/ICMLA58977.2023.00232
State	Published - 2023
Event	22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023 - Jacksonville, United States Duration: Dec 15 2023 → Dec 17 2023

Publication series

Name	Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

Conference

Conference	22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023
Country/Territory	United States
City	Jacksonville
Period	12/15/23 → 12/17/23

Funding

This material is based in part upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, under award number DE-SC0022566. It is also partially supported by a gift from Intel Neuromorphic Research Community (INRC).

Keywords

graph neural networks
neuromorphic computing
spike timing dependent plasticity
spiking neural networks

Access to Document

10.1109/ICMLA58977.2023.00232

Cite this

Cong, G., Kulkarni, S., Lim, S. H., Date, P., Snyder, S., Parsa, M., Kennedy, D., & Schuman, C. (2023). Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation. In M. Arif Wani, M. Boicu, M. Sayed-Mouchaweh, P. H. Abreu, & J. Gama (Eds.), Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023 (pp. 1541-1546). (Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA58977.2023.00232

Cong, Guojing ; Kulkarni, Shruti ; Lim, Seung Hwan et al. / Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation. Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023. editor / M. Arif Wani ; Mihai Boicu ; Moamar Sayed-Mouchaweh ; Pedro Henriques Abreu ; Joao Gama. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1541-1546 (Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023).

@inproceedings{8b609c2cbdda4ed4ac5b0cf60a2ee86e,

title = "Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation",

abstract = "Graph convolutional networks leverage both graph structures and features on nodes and edges for improved learning performance in comparison with classical machine learning approaches. Spiking neuromorphic computers natively implement network-like computation and have been shown to be successful at implementing graph learning without features. Incorporating graph features brings the challenge of efficient feature representation and balancing the contribution of topology and features in learning. In this work, we present our design of a simulated network of spiking neurons to perform semi-supervised learning on graph data using both the graph structure and the node features. We explore various design choices, present preliminary results, and discuss the opportunities for using neuromorphic computers for this task in the future.",

keywords = "graph neural networks, neuromorphic computing, spike timing dependent plasticity, spiking neural networks",

author = "Guojing Cong and Shruti Kulkarni and Lim, \{Seung Hwan\} and Prasanna Date and Shay Snyder and Maryam Parsa and Dominic Kennedy and Catherine Schuman",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023 ; Conference date: 15-12-2023 Through 17-12-2023",

year = "2023",

doi = "10.1109/ICMLA58977.2023.00232",

language = "English",

series = "Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023",

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

pages = "1541--1546",

editor = "\{Arif Wani\}, M. and Mihai Boicu and Moamar Sayed-Mouchaweh and Abreu, \{Pedro Henriques\} and Joao Gama",

booktitle = "Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023",

}

Cong, G, Kulkarni, S , Lim, SH , Date, P, Snyder, S, Parsa, M, Kennedy, D & Schuman, C 2023, Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation. in M Arif Wani, M Boicu, M Sayed-Mouchaweh, PH Abreu & J Gama (eds), Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023. Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1541-1546, 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023, Jacksonville, United States, 12/15/23. https://doi.org/10.1109/ICMLA58977.2023.00232

Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation. / Cong, Guojing; Kulkarni, Shruti ; Lim, Seung Hwan et al.
Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023. ed. / M. Arif Wani; Mihai Boicu; Moamar Sayed-Mouchaweh; Pedro Henriques Abreu; Joao Gama. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1541-1546 (Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023).

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

TY - GEN

T1 - Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation

AU - Cong, Guojing

AU - Kulkarni, Shruti

AU - Lim, Seung Hwan

AU - Date, Prasanna

AU - Snyder, Shay

AU - Parsa, Maryam

AU - Kennedy, Dominic

AU - Schuman, Catherine

PY - 2023

Y1 - 2023

N2 - Graph convolutional networks leverage both graph structures and features on nodes and edges for improved learning performance in comparison with classical machine learning approaches. Spiking neuromorphic computers natively implement network-like computation and have been shown to be successful at implementing graph learning without features. Incorporating graph features brings the challenge of efficient feature representation and balancing the contribution of topology and features in learning. In this work, we present our design of a simulated network of spiking neurons to perform semi-supervised learning on graph data using both the graph structure and the node features. We explore various design choices, present preliminary results, and discuss the opportunities for using neuromorphic computers for this task in the future.

AB - Graph convolutional networks leverage both graph structures and features on nodes and edges for improved learning performance in comparison with classical machine learning approaches. Spiking neuromorphic computers natively implement network-like computation and have been shown to be successful at implementing graph learning without features. Incorporating graph features brings the challenge of efficient feature representation and balancing the contribution of topology and features in learning. In this work, we present our design of a simulated network of spiking neurons to perform semi-supervised learning on graph data using both the graph structure and the node features. We explore various design choices, present preliminary results, and discuss the opportunities for using neuromorphic computers for this task in the future.

KW - graph neural networks

KW - neuromorphic computing

KW - spike timing dependent plasticity

KW - spiking neural networks

UR - https://www.scopus.com/pages/publications/85190149303

U2 - 10.1109/ICMLA58977.2023.00232

DO - 10.1109/ICMLA58977.2023.00232

M3 - Conference contribution

AN - SCOPUS:85190149303

T3 - Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

SP - 1541

EP - 1546

BT - Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

A2 - Arif Wani, M.

A2 - Boicu, Mihai

A2 - Sayed-Mouchaweh, Moamar

A2 - Abreu, Pedro Henriques

A2 - Gama, Joao

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

Y2 - 15 December 2023 through 17 December 2023

ER -

Cong G, Kulkarni S , Lim SH , Date P, Snyder S, Parsa M et al. Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation. In Arif Wani M, Boicu M, Sayed-Mouchaweh M, Abreu PH, Gama J, editors, Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1541-1546. (Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023). doi: 10.1109/ICMLA58977.2023.00232

Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this