TY - JOUR
T1 - Federated Multiple Tensor-on-Tensor Regression (FedMTOT) for Multimodal Data Under Data-Sharing Constraints
AU - Zhang, Zihan
AU - Mou, Shancong
AU - Reisi Gahrooei, Mostafa
AU - Pacella, Massimo
AU - Shi, Jianjun
N1 - Publisher Copyright:
© 2024 American Statistical Association and the American Society for Quality.
PY - 2024
Y1 - 2024
N2 - In recent years, diversified measurements reflect the system dynamics from a more comprehensive perspective in system modeling and analysis, such as scalars, waveform signals, images, and structured point clouds. To handle such multimodal structured high-dimensional (SHD) data, combining a large amount of data from multiple sites is necessary (i) to reduce the inherent population bias from a single site and (ii) to increase the model accuracy. However, impeded by data management policies and storage costs, data could not be easily shared or directly exchanged among different sites. Instead of simplifying or facilitating the data query process, we propose a federated multiple tensor-on-tensor regression (FedMTOT) framework to train the individual system model locally using (i) its own data and (ii) data features (not data itself) from other sites. Specifically, federated computation is executed based on alternating direction method of multipliers (ADMM) to satisfy data-sharing requirements, while the individual model at each site can still benefit from feature knowledge from other sites to improve its own model accuracy. Finally, two simulations and two case studies validate the superiority of the proposed FedMTOT framework.
AB - In recent years, diversified measurements reflect the system dynamics from a more comprehensive perspective in system modeling and analysis, such as scalars, waveform signals, images, and structured point clouds. To handle such multimodal structured high-dimensional (SHD) data, combining a large amount of data from multiple sites is necessary (i) to reduce the inherent population bias from a single site and (ii) to increase the model accuracy. However, impeded by data management policies and storage costs, data could not be easily shared or directly exchanged among different sites. Instead of simplifying or facilitating the data query process, we propose a federated multiple tensor-on-tensor regression (FedMTOT) framework to train the individual system model locally using (i) its own data and (ii) data features (not data itself) from other sites. Specifically, federated computation is executed based on alternating direction method of multipliers (ADMM) to satisfy data-sharing requirements, while the individual model at each site can still benefit from feature knowledge from other sites to improve its own model accuracy. Finally, two simulations and two case studies validate the superiority of the proposed FedMTOT framework.
KW - Data-sharing compliance
KW - Federated learning
KW - Multimodal data fusion
KW - Structured high-dimensional data
UR - http://www.scopus.com/inward/record.url?scp=85192348630&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85192348630&partnerID=8YFLogxK
U2 - 10.1080/00401706.2024.2333506
DO - 10.1080/00401706.2024.2333506
M3 - Article
AN - SCOPUS:85192348630
SN - 0040-1706
JO - Technometrics
JF - Technometrics
ER -