Explaining Memristive Reservoir Computing Through Evolving Feature Attribution

Xinming SHI; Zilu WANG; Leandro L. MINKU; Xin YAO

doi:10.1145/3583133.3590619

Explaining Memristive Reservoir Computing Through Evolving Feature Attribution

Xinming SHI, Zilu WANG, Leandro L. MINKU, Xin YAO

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

1 Citation (Scopus)

Abstract

Memristive Reservoir Computing (MRC) is a promising computing architecture for time series tasks, but lacks explainability, leading to unreliable predictions. To address this issue, we propose an evolutionary framework to explain the time series predictions of MRC systems. Our proposed approach attributes the feature importance of the time series via an evolutionary approach to explain the predictions. Our experiments show that our approach successfully identified the most influential factors, demonstrating the effectiveness of our design and its superiority in terms of explanation compared to state-of-the-art methods. © 2023 Copyright held by the owner/author(s).

Original language	English
Title of host publication	GECCO 2023 Companion : Proceedings of the 2023 Genetic and Evolutionary Computation Conference Companion
Editors	Sara SILVA, Luís PAQUETE
Place of Publication	New York
Publisher	Association for Computing Machinery, Inc
Pages	683-686
Number of pages	4
ISBN (Print)	9798400701207
DOIs	https://doi.org/10.1145/3583133.3590619
Publication status	Published - 15 Jul 2023
Externally published	Yes
Event	Genetic and Evolutionary Computation Conference 2023 - Lisbon, Portugal Duration: 15 Jul 2023 → 19 Jul 2023

Conference

Conference	Genetic and Evolutionary Computation Conference 2023
Abbreviated title	GECCO’23 Companion
Country/Territory	Portugal
City	Lisbon
Period	15/07/23 → 19/07/23

Bibliographical note

This work was supported by NSFC (Grant No. 62250710682), the Research Institute of Trustworthy Autonomous Systems (RITAS), the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), the Program for Guangdong Introducing Innovative and Enterpreneurial Teams (Grant No. 2017ZT07X386), the Shenzhen Science and Technology Program (Grant No. KQTD2016112514355531).

Keywords

evolutionary algorithm
Explainability
memristor
reservoir computing

Access to Document

10.1145/3583133.3590619

Cite this

@inproceedings{33a66da7bd2b44d2850d353e0d31e962,

title = "Explaining Memristive Reservoir Computing Through Evolving Feature Attribution",

abstract = "Memristive Reservoir Computing (MRC) is a promising computing architecture for time series tasks, but lacks explainability, leading to unreliable predictions. To address this issue, we propose an evolutionary framework to explain the time series predictions of MRC systems. Our proposed approach attributes the feature importance of the time series via an evolutionary approach to explain the predictions. Our experiments show that our approach successfully identified the most influential factors, demonstrating the effectiveness of our design and its superiority in terms of explanation compared to state-of-the-art methods. {\textcopyright} 2023 Copyright held by the owner/author(s).",

keywords = "evolutionary algorithm, Explainability, memristor, reservoir computing",

author = "Xinming SHI and Zilu WANG and MINKU, {Leandro L.} and Xin YAO",

note = "This work was supported by NSFC (Grant No. 62250710682), the Research Institute of Trustworthy Autonomous Systems (RITAS), the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), the Program for Guangdong Introducing Innovative and Enterpreneurial Teams (Grant No. 2017ZT07X386), the Shenzhen Science and Technology Program (Grant No. KQTD2016112514355531).; Genetic and Evolutionary Computation Conference 2023, GECCO{\textquoteright}23 Companion ; Conference date: 15-07-2023 Through 19-07-2023",

year = "2023",

month = jul,

day = "15",

doi = "10.1145/3583133.3590619",

language = "English",

isbn = "9798400701207",

pages = "683--686",

editor = "SILVA, {Sara } and Lu{\'i}s PAQUETE",

booktitle = "GECCO 2023 Companion : Proceedings of the 2023 Genetic and Evolutionary Computation Conference Companion",

publisher = "Association for Computing Machinery, Inc",

}

SHI, X, WANG, Z, MINKU, LL & YAO, X 2023, Explaining Memristive Reservoir Computing Through Evolving Feature Attribution. in S SILVA & L PAQUETE (eds), GECCO 2023 Companion : Proceedings of the 2023 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, New York, pp. 683-686, Genetic and Evolutionary Computation Conference 2023, Lisbon, Portugal, 15/07/23. https://doi.org/10.1145/3583133.3590619

Explaining Memristive Reservoir Computing Through Evolving Feature Attribution. / SHI, Xinming; WANG, Zilu; MINKU, Leandro L. et al.
GECCO 2023 Companion : Proceedings of the 2023 Genetic and Evolutionary Computation Conference Companion. ed. / Sara SILVA; Luís PAQUETE. New York: Association for Computing Machinery, Inc, 2023. p. 683-686.

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - Explaining Memristive Reservoir Computing Through Evolving Feature Attribution

AU - SHI, Xinming

AU - WANG, Zilu

AU - MINKU, Leandro L.

AU - YAO, Xin

N1 - This work was supported by NSFC (Grant No. 62250710682), the Research Institute of Trustworthy Autonomous Systems (RITAS), the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), the Program for Guangdong Introducing Innovative and Enterpreneurial Teams (Grant No. 2017ZT07X386), the Shenzhen Science and Technology Program (Grant No. KQTD2016112514355531).

PY - 2023/7/15

Y1 - 2023/7/15

N2 - Memristive Reservoir Computing (MRC) is a promising computing architecture for time series tasks, but lacks explainability, leading to unreliable predictions. To address this issue, we propose an evolutionary framework to explain the time series predictions of MRC systems. Our proposed approach attributes the feature importance of the time series via an evolutionary approach to explain the predictions. Our experiments show that our approach successfully identified the most influential factors, demonstrating the effectiveness of our design and its superiority in terms of explanation compared to state-of-the-art methods. © 2023 Copyright held by the owner/author(s).

AB - Memristive Reservoir Computing (MRC) is a promising computing architecture for time series tasks, but lacks explainability, leading to unreliable predictions. To address this issue, we propose an evolutionary framework to explain the time series predictions of MRC systems. Our proposed approach attributes the feature importance of the time series via an evolutionary approach to explain the predictions. Our experiments show that our approach successfully identified the most influential factors, demonstrating the effectiveness of our design and its superiority in terms of explanation compared to state-of-the-art methods. © 2023 Copyright held by the owner/author(s).

KW - evolutionary algorithm

KW - Explainability

KW - memristor

KW - reservoir computing

UR - http://www.scopus.com/inward/record.url?scp=85169064550&partnerID=8YFLogxK

U2 - 10.1145/3583133.3590619

DO - 10.1145/3583133.3590619

M3 - Conference paper (refereed)

SN - 9798400701207

SP - 683

EP - 686

BT - GECCO 2023 Companion : Proceedings of the 2023 Genetic and Evolutionary Computation Conference Companion

A2 - SILVA, Sara

A2 - PAQUETE, Luís

PB - Association for Computing Machinery, Inc

CY - New York

T2 - Genetic and Evolutionary Computation Conference 2023

Y2 - 15 July 2023 through 19 July 2023

ER -

Explaining Memristive Reservoir Computing Through Evolving Feature Attribution

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this