# Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecasting

arXiv: https://arxiv.org/abs/2302.10347 · HTML: https://mlsanity.com/paper/2302.10347/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 64 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Builds on (most cited first, 13 of 13)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Online Learning: A Comprehensive Survey](https://mlsanity.com/paper/1802.02871/) (2018)
- [Minimal Gated Unit for Recurrent Neural Networks](https://mlsanity.com/paper/1603.09420/) (2016)
- [A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks](https://mlsanity.com/paper/1907.02649/) (2019)
- [Online Learning for Time Series Prediction](https://mlsanity.com/paper/1302.6927/) (2013)
- [Capacity and Trainability in Recurrent Neural Networks](https://mlsanity.com/paper/1611.09913/) (2016)
- [Towards AutoML in the presence of Drift: first results](https://mlsanity.com/paper/1907.10772/) (2019)
- [Adaptation Strategies for Automated Machine Learning on Evolving Data](https://mlsanity.com/paper/2006.06480/) (2020)
- [Online AutoML: An adaptive AutoML framework for online learning](https://mlsanity.com/paper/2201.09750/) (2022)
- [Investigating Recurrent Neural Network Memory Structures using Neuro-Evolution](https://mlsanity.com/paper/1902.02390/) (2019)
- [Learning Simpler Language Models with the Differential State Framework](https://mlsanity.com/paper/1703.08864/) (2017)
- [Privacy-preserving Online AutoML for Domain-Specific Face Detection](https://mlsanity.com/paper/2203.08399/) (2022)
- [ONE-NAS: An Online NeuroEvolution based Neural Architecture Search for Time Series Forecasting](https://mlsanity.com/paper/2202.13471/) (2022)

## Built on by (most cited first, 2 of 2)

- [Optimizing Time Series Forecasting Architectures: A Hierarchical Neural Architecture Search Approach](https://mlsanity.com/paper/2406.05088/) (2024)
- [Neural Architecture Search for global multi-step Forecasting of Energy Production Time Series](https://mlsanity.com/paper/2511.00035/) (2025)

## Abstract (arXiv)

Time series forecasting (TSF) is one of the most important tasks in data science given the fact that accurate time series (TS) predictive models play a major role across a wide variety of domains including finance, transportation, health care, and power systems. Real-world utilization of machine learning (ML) typically involves (pre-)training models on collected, historical data and then applying them to unseen data points. However, in real-world applications, time series data streams are usually non-stationary and trained ML models usually, over time, face the problem of data or concept drift. To address this issue, models must be periodically retrained or redesigned, which takes significant human and computational resources. Additionally, historical data may not even exist to re-train or re-design model with. As a result, it is highly desirable that models are designed and trained in an online fashion. This work presents the Online NeuroEvolution-based Neural Architecture Search (ONE-NAS) algorithm, which is a novel neural architecture search method capable of automatically designing and dynamically training recurrent neural networks (RNNs) for online forecasting tasks. Without any pre-training, ONE-NAS utilizes populations of RNNs that are continuously updated with new network structures and weights in response to new multivariate input data. ONE-NAS is tested on real-world, large-scale multivariate wind turbine data as well as the univariate Dow Jones Industrial Average (DJIA) dataset. Results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods, including online linear regression, fixed long short-term memory (LSTM) and gated recurrent unit (GRU) models trained online, as well as state-of-the-art, online ARIMA strategies.