.png){kind=icon}
.png){kind=icon}
Return
Multimodal Multiobjective Neural Architecture Search for Lightweight and Failure-Resilient Time Series Forecasting
.png){kind=icon}
PRE
AI
Y
H
刘
DOI：10.1109/tevc.2026.3658547.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Time series forecasting (TSF) plays a pivotal role in decision-making and risk mitigation by predicting future values from historical observations. Despite significant improvements in forecasting accuracy, existing TSF models face two critical challenges. Increasing computational complexity hinders deployment on resource-constrained platforms, and vulnerability to random failures compromises prediction stability. To address these issues, we propose M3NAS-TSF, a multimodal multiobjective neural architecture search (NAS) framework that automates the design of lightweight and failure-resilient TSF models. Specifically, to address computational complexity, we introduce a modular time series super-net (MoTS-Net) that defines a flexible and compact search space, enabling the discovery of architectures with reduced model size. To enhance failure resilience, we develop a multimodal multiobjective NAS algorithm that promotes architectural diversity through an architecture-aware niching strategy and an architectural diversity distance (ADD) metric, ensuring a broad set of robust candidate models. We also propose a node distribution heatmap (NDH) and a structural entropy (SE) index to assess architectural diversity without ground-truth Pareto sets. Extensive experiments on 40 forecasting cases demonstrate that M3NAS-TSF outperforms six representative baselines, achieving superior forecasting accuracy (the maximum reduction in the root-mean-square error (RMSE) reached 14.50%) with a smaller model size while maintaining greater architectural diversity for failure resilience.
Keywords:
Multimodal multiobjective optimization
neural architecture search (NAS)
time series forecasting (TSF)
Journal
IF:
12
Papers:
1.8K
Citations:
2.4W
Organization
Cited Papers