Details
| Original language | English |
|---|---|
| Title of host publication | KDD `23 |
| Subtitle of host publication | Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 3140-3150 |
| Number of pages | 11 |
| ISBN (electronic) | 9798400701030 |
| Publication status | Published - 4 Aug 2023 |
| Event | 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 - Long Beach, United States Duration: 6 Aug 2023 → 10 Aug 2023 |
Publication series
| Name | Proceedings 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
- Computer Science(all)
- Software
- Computer Science(all)
- Information Systems
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
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 proceeding › Conference contribution › Research › peer review
}
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 -