SPS Webinar: Devising Transformers as an Autoencoder for Unsupervised Multivariate Time Series Imputation
Date: 12 June 2024
Time: 10:00 AM ET (New York Time)
Presenter(s): Dr. Aykut Koç
Original article publicly available for download on the day of the webinar for 48 hours:: Download article
Abstract
Time-series data processing is essential across various fields, including healthcare, transportation, and weather forecasting. Multivariate time-series data, in particular, exhibit a correlation pattern over a common independent variable. This is illustrated by concurrent sensor readings in applications like autonomous driving or multiple channels in data collection devices used in medical diagnoses. However, the increasing incidence of data acquisition failures, including sensor malfunctions and human errors, results in gaps and substantial loss of information. The presenter will propose a novel method called Multivariate Time-Series Imputation with Transformers (MTSIT) to tackle these challenges. This method employs an unsupervised autoencoder model with a transformer encoder to leverage unlabeled observed data for simultaneous reconstruction and imputation of multivariate time series. The MTSIT strategy presents an input sequence with gaps (missing patterns) to the transformer encoder. The final encoder block produces an output sequence that is linearly transformed into the imputed sequence. The Mean Squared Error (MSE) is subsequently computed between the missing values and their predicted imputations, guiding the network’s training toward minimizing the MSE.
Biography
Aykut Koç (M’16 – SM’20) received the B.S. degree in electrical and electronics engineering from Bilkent University, Ankara, Türkiye, in 2005, the M.S. degree in electrical engineering, the M.S. degree in management science and engineering, and the Ph.D. degree in electrical engineering from Stanford University, Stanford, CA, USA, in 2007, 2009, and 2011, respectively. His research interests include machine learning and signal processing extending into natural language and graph signal processing.
He is a Faculty Member with the Department of Electrical and Electronics Engineering and National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara, Türkiye. He has authored or coauthored more than 80 research papers, one book chapter, and issued four patents.
Dr. Koç is currently an Associate Editor for IEEE Signal Processing Letters, IEEE Transactions on Signal and Information Processing Over Networks, and IEEE Transactions on Circuits and Systems for Video Technology. He was the recipient of the 2023 Science Academy Young Scientists Award (BAGEP).