As reviewers noticed, detailed description of the experiments is provided in the3 supplement. Wealso6 switched to a finer discretization of 1 minute on Physionet dataset, instead of 6 minutes. Modeling state-interactions via26 an ODE allows better generalization outside the training interval compared to directly modeling a function of time.27 Using an ODE-RNN as a decoder is a possible extension.

Recently, model-based reinforcement learning algorithms have demonstrated remarkable efficacy in visual input environments.

Graph-based semi-supervised learning isvery important for manyclassification tasks, but most existing methods assume that all labelled nodes are randomly sampled.

Time series forecasting plays akeyrole in informing industrial and business decisions [17,24,8], while segmentation isuseful forunderstanding biological andphysicalsystems [40,45,34].

More advanced methods dealwith missing data byautoregressivelyreplacing missing observations with predicted ones, eventually using bidirectional architectures [5,6]toexploit both forwardandbackwardtemporal dependencies.