FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

Research Organisations

External Research Organisations

  • University of Hildesheim
View graph of relations

Details

Original languageEnglish
Title of host publicationKDD `23
Subtitle of host publicationProceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery (ACM)
Pages3140-3150
Number of pages11
ISBN (electronic)9798400701030
Publication statusPublished - 4 Aug 2023
Event29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 - Long Beach, United States
Duration: 6 Aug 202310 Aug 2023

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Abstract

Increasing privacy concerns have led to decentralized and federated machine learning techniques that allow individual clients to consult and train models collaboratively without sharing private information. Some of these applications, such as medical and healthcare, require the final decisions to be interpretable. One common form of data in these applications is multivariate time series, where deep neural networks, especially convolutional neural networks based approaches, have established excellent performance in their classification tasks. However, promising results and performance of deep learning models are a black box, and their decisions cannot always be guaranteed and trusted. While several approaches address the interpretability of deep learning models for multivariate time series data in a centralized environment, less effort has been made in a federated setting. In this work, we introduce FLAMES2Graph, a new horizontal federated learning framework designed to interpret the deep learning decisions of each client. FLAMES2Graph extracts and visualizes those input subsequences that are highly activated by a convolutional neural network. Besides, an evolution graph is created to capture the temporal dependencies between the extracted distinct subsequences. The federated learning clients only share this temporal evolution graph with the centralized server instead of trained model weights to create a global evolution graph. Our extensive experiments on various datasets from well-known multivariate benchmarks indicate that the FLAMES2Graph framework significantly outperforms other state-of-the-art federated methods while keeping privacy and augmenting network decision interpretation.

Keywords

    federated learning, interpretability, neural networks, time series

ASJC Scopus subject areas

Cite this

FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework. / Younis, Raneen; Ahmadi, Zahra; Hakmeh, Abdul et al.
KDD `23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM), 2023. p. 3140-3150 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Younis, R, Ahmadi, Z, Hakmeh, A & Fisichella, M 2023, FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework. in KDD `23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery (ACM), pp. 3140-3150, 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023, Long Beach, United States, 6 Aug 2023. https://doi.org/10.1145/3580305.3599354
Younis, R., Ahmadi, Z., Hakmeh, A., & Fisichella, M. (2023). FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework. In KDD `23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 3140-3150). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery (ACM). https://doi.org/10.1145/3580305.3599354
Younis R, Ahmadi Z, Hakmeh A, Fisichella M. FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework. In KDD `23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM). 2023. p. 3140-3150. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3580305.3599354
Younis, Raneen ; Ahmadi, Zahra ; Hakmeh, Abdul et al. / FLAMES2Graph : An Interpretable Federated Multivariate Time Series Classification Framework. KDD `23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM), 2023. pp. 3140-3150 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).
Download
@inproceedings{4b76a9eca571458b89d3c822c2b41cea,
title = "FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework",
abstract = "Increasing privacy concerns have led to decentralized and federated machine learning techniques that allow individual clients to consult and train models collaboratively without sharing private information. Some of these applications, such as medical and healthcare, require the final decisions to be interpretable. One common form of data in these applications is multivariate time series, where deep neural networks, especially convolutional neural networks based approaches, have established excellent performance in their classification tasks. However, promising results and performance of deep learning models are a black box, and their decisions cannot always be guaranteed and trusted. While several approaches address the interpretability of deep learning models for multivariate time series data in a centralized environment, less effort has been made in a federated setting. In this work, we introduce FLAMES2Graph, a new horizontal federated learning framework designed to interpret the deep learning decisions of each client. FLAMES2Graph extracts and visualizes those input subsequences that are highly activated by a convolutional neural network. Besides, an evolution graph is created to capture the temporal dependencies between the extracted distinct subsequences. The federated learning clients only share this temporal evolution graph with the centralized server instead of trained model weights to create a global evolution graph. Our extensive experiments on various datasets from well-known multivariate benchmarks indicate that the FLAMES2Graph framework significantly outperforms other state-of-the-art federated methods while keeping privacy and augmenting network decision interpretation.",
keywords = "federated learning, interpretability, neural networks, time series",
author = "Raneen Younis and Zahra Ahmadi and Abdul Hakmeh and Marco Fisichella",
note = "Funding Information: This research was partially funded by the Federal Ministry of Education and Research (BMBF), Germany under the project LeibnizK-ILabor with grant No. 01DD20003. The research was performed while the first author was finically covered by the German Federal Ministry of Education and Research (BMBF), Germany under the project ProKI-Hannover with grant No.60172523. ; 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 ; Conference date: 06-08-2023 Through 10-08-2023",
year = "2023",
month = aug,
day = "4",
doi = "10.1145/3580305.3599354",
language = "English",
series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery (ACM)",
pages = "3140--3150",
booktitle = "KDD `23",
address = "United States",

}

Download

TY - GEN

T1 - FLAMES2Graph

T2 - 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023

AU - Younis, Raneen

AU - Ahmadi, Zahra

AU - Hakmeh, Abdul

AU - Fisichella, Marco

N1 - Funding Information: This research was partially funded by the Federal Ministry of Education and Research (BMBF), Germany under the project LeibnizK-ILabor with grant No. 01DD20003. The research was performed while the first author was finically covered by the German Federal Ministry of Education and Research (BMBF), Germany under the project ProKI-Hannover with grant No.60172523.

PY - 2023/8/4

Y1 - 2023/8/4

N2 - Increasing privacy concerns have led to decentralized and federated machine learning techniques that allow individual clients to consult and train models collaboratively without sharing private information. Some of these applications, such as medical and healthcare, require the final decisions to be interpretable. One common form of data in these applications is multivariate time series, where deep neural networks, especially convolutional neural networks based approaches, have established excellent performance in their classification tasks. However, promising results and performance of deep learning models are a black box, and their decisions cannot always be guaranteed and trusted. While several approaches address the interpretability of deep learning models for multivariate time series data in a centralized environment, less effort has been made in a federated setting. In this work, we introduce FLAMES2Graph, a new horizontal federated learning framework designed to interpret the deep learning decisions of each client. FLAMES2Graph extracts and visualizes those input subsequences that are highly activated by a convolutional neural network. Besides, an evolution graph is created to capture the temporal dependencies between the extracted distinct subsequences. The federated learning clients only share this temporal evolution graph with the centralized server instead of trained model weights to create a global evolution graph. Our extensive experiments on various datasets from well-known multivariate benchmarks indicate that the FLAMES2Graph framework significantly outperforms other state-of-the-art federated methods while keeping privacy and augmenting network decision interpretation.

AB - Increasing privacy concerns have led to decentralized and federated machine learning techniques that allow individual clients to consult and train models collaboratively without sharing private information. Some of these applications, such as medical and healthcare, require the final decisions to be interpretable. One common form of data in these applications is multivariate time series, where deep neural networks, especially convolutional neural networks based approaches, have established excellent performance in their classification tasks. However, promising results and performance of deep learning models are a black box, and their decisions cannot always be guaranteed and trusted. While several approaches address the interpretability of deep learning models for multivariate time series data in a centralized environment, less effort has been made in a federated setting. In this work, we introduce FLAMES2Graph, a new horizontal federated learning framework designed to interpret the deep learning decisions of each client. FLAMES2Graph extracts and visualizes those input subsequences that are highly activated by a convolutional neural network. Besides, an evolution graph is created to capture the temporal dependencies between the extracted distinct subsequences. The federated learning clients only share this temporal evolution graph with the centralized server instead of trained model weights to create a global evolution graph. Our extensive experiments on various datasets from well-known multivariate benchmarks indicate that the FLAMES2Graph framework significantly outperforms other state-of-the-art federated methods while keeping privacy and augmenting network decision interpretation.

KW - federated learning

KW - interpretability

KW - neural networks

KW - time series

UR - http://www.scopus.com/inward/record.url?scp=85171322761&partnerID=8YFLogxK

U2 - 10.1145/3580305.3599354

DO - 10.1145/3580305.3599354

M3 - Conference contribution

AN - SCOPUS:85171322761

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 3140

EP - 3150

BT - KDD `23

PB - Association for Computing Machinery (ACM)

Y2 - 6 August 2023 through 10 August 2023

ER -

By the same author(s)