HypperSteer: Hypothetical Steering and Data Perturbation in Sequence Prediction with Deep Learning
This addresses a practical problem for practitioners in fields like healthcare who need to interact with and interpret deep learning models for sequence prediction, though it is incremental as it builds on existing visual analytics approaches.
The paper tackles the lack of interactive tools for what-if analysis and data perturbation in deep learning-based sequence prediction, presenting HypperSteer, a model-agnostic visual analytics tool that enables users to steer hypothetical testing and perturb data to achieve desired outcomes, such as guiding patient data for treatment goals.
Deep Recurrent Neural Networks (RNN) continues to find success in predictive decision-making with temporal event sequences. Recent studies have shown the importance and practicality of visual analytics in interpreting deep learning models for real-world applications. However, very limited work enables interactions with deep learning models and guides practitioners to form hypotheticals towards the desired prediction outcomes, especially for sequence prediction. Specifically, no existing work has addressed the what-if analysis and value perturbation along different time-steps for sequence outcome prediction. We present a model-agnostic visual analytics tool, HypperSteer, that steers hypothetical testing and allows users to perturb data for sequence predictions interactively. We showcase how HypperSteer helps in steering patient data to achieve desired treatment outcomes and discuss how HypperSteer can serve as a comprehensive solution for other practical scenarios.