A Scalable Multi-Task Model for Virtual Sensors
cs.LG
Submitted: 2026-01-28
Updated: 2026-10-28
Comments: 24 pages in total, 17 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: Virtual sensors replace expensive physical sensors in critical applications through machine learning by predicting target signals from available measurements.
Terminology
Abstract
Virtual sensors replace expensive physical sensors in critical applications through machine learning by predicting target signals from available measurements. Existing virtual sensor approaches require application-specific models with hand-selected inputs for each sensor, cannot leverage task synergies, and lack consistent benchmarks. While emerging time series foundation models offer general-purpose, pretrained solutions in other domains, they are computationally expensive and limited to predicting their input signals, making them incompatible with virtual sensors. We introduce the first multi-task model for virtual sensors addressing both limitations. Our unified model can simultaneously predict diverse virtual sensors exploiting synergies while maintaining computational efficiency. It learns relevant input signals for each virtual sensor, eliminating expert knowledge requirements while adding explainability. In our large-scale evaluation on three standard benchmarks and an application-specific dataset with over 18 billion samples, our architecture reduces computation time by up to 415x and memory requirements by 951x, while maintaining or even improving predictive quality compared to unified baselines. Compared to existing isolated models for a single virtual sensor, our unified approach generates superior predictions at similar inference speed while scaling gracefully to hundreds of virtual sensors with nearly constant parameter count, enabling practical deployment in large-scale sensor networks.
Sources
- A decoder-only foundation model for time-series forecasting
- Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
- TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
- Unified Training of Universal Time Series Forecasting Transformers
- Toto: Time Series Optimized Transformer for Observability
- Long-term Forecasting with TiDE: Time-series Dense Encoder
- Zero-Shot Time Series Forecasting with Covariates via In-Context Learning
- Chronos-2: From Univariate to Universal Forecasting
- Dataset-Driven Channel Masks in Transformers for Multivariate Time Series
- DGCformer: Deep Graph Clustering Transformer for Multivariate Time Series Forecasting
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis