Semi-supervised biomedical translation with cycle Wasserstein regression GaNs
Author(s)
McDermott, Matthew; Yan, Tom; Naumann, Tristan; Hunt, Nathan; Suresh, Harini S.; Szolovits, Peter; Ghassemi, Marzyeh; ... Show more Show less
DownloadAccepted version (568.1Kb)
Terms of use
Metadata
Show full item recordAbstract
The biomedical field offers many learning tasks that share unique challenges: large amounts of unpaired data, and a high cost to generate labels. In this work, we develop a method to address these issues with semi-supervised learning in regression tasks (e.g., translation from source to target). Our model uses adversarial signals to learn from unpaired datapoints, and imposes a cycle-loss reconstruction error penalty to regularize mappings in either direction against one another. We first evaluate our method on synthetic experiments, demonstrating two primary advantages of the system: 1) distribution matching via the adversarial loss and 2) regularization towards invertible mappings via the cycle loss. We then show a regularization effect and improved performance when paired data is supplemented by additional unpaired data on two real biomedical regression tasks: estimating the physiological effect of medical treatments, and extrapolating gene expression (transcriptomics) signals. Our proposed technique is a promising initial step towards more robust use of adversarial signals in semi-supervised regression, and could be useful for other tasks (e.g., causal inference or modality translation) in the biomedical field.
Date issued
2018Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryJournal
Proceedings of the AAAI Conference on Artificial Intelligence
Citation
McDermott, Matthew B. A. et al. "Semi-Supervised Biomedical Translation with Cycle Wasserstein Regression GANs." AAAI Conference on Artificial Intelligence, February 2018, New Orleans, AAAI, 2018.
Version: Author's final manuscript
ISSN
2159-5399