# NeuralPrefix: A Zero-shot Sensory Data Imputation Plugin

arXiv: https://arxiv.org/abs/2502.05883 · HTML: https://mlsanity.com/paper/2502.05883/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 9 Feb 2025.

## Builds on (most cited first, 19 of 19)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [A Review of Generalized Zero-Shot Learning Methods](https://mlsanity.com/paper/2011.08641/) (2020)
- [Delving Deeper into Convolutional Networks for Learning Video Representations](https://mlsanity.com/paper/1511.06432/) (2015)
- [Deep Learning for Multivariate Time Series Imputation: A Survey](https://mlsanity.com/paper/2402.04059/) (2024)
- [Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation](https://mlsanity.com/paper/2010.08188/) (2020)
- [MCFlow: Monte Carlo Flow Models for Data Imputation](https://mlsanity.com/paper/2003.12628/) (2020)
- [Generative Adversarial Networks for Spatio-temporal Data: A Survey](https://mlsanity.com/paper/2008.08903/) (2020)
- [TSI-Bench: Benchmarking Time Series Imputation](https://mlsanity.com/paper/2406.12747/) (2024)
- [Towards Domain-Independent and Real-Time Gesture Recognition Using mmWave Signal](https://mlsanity.com/paper/2111.06195/) (2021)
- [Deep Learning for Radio-based Human Sensing: Recent Advances and Future Directions](https://mlsanity.com/paper/2010.12717/) (2020)
- [Simple Video Generation using Neural ODEs](https://mlsanity.com/paper/2109.03292/) (2021)
- [Learning Dynamics from Noisy Measurements using Deep Learning with a Runge-Kutta Constraint](https://mlsanity.com/paper/2109.11446/) (2021)
- [EMFlow: Data Imputation in Latent Space via EM and Deep Flow Models](https://mlsanity.com/paper/2106.04804/) (2021)
- [LADDER: An Efficient Framework for Video Frame Interpolation](https://mlsanity.com/paper/2404.11108/) (2024)
- [Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE](https://mlsanity.com/paper/2112.10960/) (2021)

## Abstract (arXiv)

Real-world sensing challenges such as sensor failures, communication issues, and power constraints lead to data intermittency. An issue that is known to undermine the traditional classification task that assumes a continuous data stream. Previous works addressed this issue by designing bespoke solutions (i.e. task-specific and/or modality-specific imputation). These approaches, while effective for their intended purposes, had limitations in their applicability across different tasks and sensor modalities. This raises an important question: Can we build a task-agnostic imputation pipeline that is transferable to new sensors without requiring additional training? In this work, we formalise the concept of zero-shot imputation and propose a novel approach that enables the adaptation of pre-trained models to handle data intermittency. This framework, named NeuralPrefix, is a generative neural component that precedes a task model during inference, filling in gaps caused by data intermittency. NeuralPrefix is built as a continuous dynamical system, where its internal state can be estimated at any point in time by solving an Ordinary Differential Equation (ODE). This approach allows for a more versatile and adaptable imputation method, overcoming the limitations of task-specific and modality-specific solutions. We conduct a comprehensive evaluation of NeuralPrefix on multiple sensory datasets, demonstrating its effectiveness across various domains. When tested on intermittent data with a high 50% missing data rate, NeuralPreifx accurately recovers all the missing samples, achieving SSIM score between 0.93-0.96. Zero-shot evaluations show that NeuralPrefix generalises well to unseen datasets, even when the measurements come from a different modality.