# Modular Deep Learning for Multivariate Time-Series: Decoupling Imputation and Downstream Tasks

arXiv: https://arxiv.org/abs/2411.03941 · HTML: https://mlsanity.com/paper/2411.03941/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 6 Nov 2024.

## Builds on (most cited first, 20 of 20)

- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models](https://mlsanity.com/paper/2208.09399/) (2022)
- [GP-VAE: Deep Probabilistic Time Series Imputation](https://mlsanity.com/paper/1907.04155/) (2019)
- [SAITS: Self-Attention-based Imputation for Time Series](https://mlsanity.com/paper/2202.08516/) (2022)
- [Handling Incomplete Heterogeneous Data using VAEs](https://mlsanity.com/paper/1807.03653/) (2018)
- [Is a Modular Architecture Enough?](https://mlsanity.com/paper/2206.02713/) (2022)
- [VIGAN: Missing View Imputation with Generative Adversarial Networks](https://mlsanity.com/paper/1708.06724/) (2017)
- [Uncertainty-Aware Variational-Recurrent Imputation Network for Clinical Time Series](https://mlsanity.com/paper/2003.00662/) (2020)
- [Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputation](https://mlsanity.com/paper/2305.07247/) (2023)
- [Handling missing values in healthcare data: A systematic review of deep learning-based imputation techniques](https://mlsanity.com/paper/2210.08258/) (2022)
- [Transfer Learning for Clinical Time Series Analysis using Deep Neural Networks](https://mlsanity.com/paper/1904.00655/) (2019)
- [Probabilistic Imputation for Time-series Classification with Missing Data](https://mlsanity.com/paper/2308.06738/) (2023)
- [An end-to-end Generative Retrieval Method for Sponsored Search Engine --Decoding Efficiently into a Closed Target Domain](https://mlsanity.com/paper/1902.00592/) (2019)
- [Review for Handling Missing Data with special missing mechanism](https://mlsanity.com/paper/2404.04905/) (2024)
- [How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputation](https://mlsanity.com/paper/2407.08442/) (2024)
- [Modularity in Deep Learning: A Survey](https://mlsanity.com/paper/2310.01154/) (2023)

## Abstract (arXiv)

Missing values are pervasive in large-scale time-series data, posing challenges for reliable analysis and decision-making. Many neural architectures have been designed to model and impute the complex and heterogeneous missingness patterns of such data. Most existing methods are end-to-end, rendering imputation tightly coupled with downstream predictive tasks and leading to limited reusability of the trained model, reduced interpretability, and challenges in assessing model quality. In this paper, we call for a modular approach that decouples imputation and downstream tasks, enabling independent optimisation and greater adaptability. Using the largest open-source Python library for deep learning-based time-series analysis, PyPOTS, we evaluate a modular pipeline across six state-of-the-art models that perform imputation and prediction on seven datasets spanning multiple domains. Our results show that a modular approach maintains high performance while prioritising flexibility and reusability - qualities that are crucial for real-world applications. Through this work, we aim to demonstrate how modularity can benefit multivariate time-series analysis, achieving a balance between performance and adaptability.