mlsanityData to 7 Oct 2026

Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations

arXiv 2402.12598 ↗First posted 19 Feb 2024cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Virtual sensing techniques allow for inferring signals at new unmonitored locations by exploiting spatio-temporal measurements coming from physical sensors at different locations. However, as the sensor coverage becomes sparse due to costs or other constraints, physical proximity cannot be used to support interpolation. In this paper, we overcome this challenge by leveraging dependencies between the target variable and a set of correlated variables (covariates) that can frequently be associated with each location of interest. From this viewpoint, covariates provide partial observability, and the problem consists of inferring values for unobserved channels by exploiting observations at other locations to learn how such variables can correlate. We introduce a novel graph-based methodology to exploit such relationships and design a graph deep learning architecture, named GgNet, implementing the framework. The proposed approach relies on propagating information over a nested graph structure that is used to learn dependencies between variables as well as locations. GgNet is extensively evaluated under different virtual sensing scenarios, demonstrating higher reconstruction accuracy compared to the state-of-the-art.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 28 of its 61 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

28 of 61 references.

References · 28

  1. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  2. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  3. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  4. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  5. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  6. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 349
  7. 2018Neural Relational Inference for Interacting Systemscited by 339
  8. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 288
  9. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 234
  10. 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 171
  11. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 167
  12. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
16 more
  1. 2019A Gentle Introduction to Deep Learning for Graphscited by 107
  2. 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 93
  3. 2020Inductive Graph Neural Networks for Spatiotemporal Krigingcited by 90
  4. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  5. 2020Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globalitycited by 70
  6. 2022Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observationscited by 64
  7. 2023Taming Local Effects in Graph-based Spatiotemporal Forecastingcited by 37
  8. 2023Kriging Convolutional Networkscited by 30
  9. 2021Spatial Aggregation and Temporal Convolution Networks for Real-time Krigingcited by 27
  10. 2023INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Krigingcited by 27
  11. 2019CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputationcited by 24
  12. 2022Sparse Graph Learning from Spatiotemporal Time Seriescited by 22
  13. 2023Graph Neural Processes for Spatio-Temporal Extrapolationcited by 18
  14. 2017Time Series Cluster Kernel for Learning Similarities between Multivariate Time Series with Missing Datacited by 11
  15. 2022Forecasting Unobserved Node States with spatio-temporal Graph Neural Networkscited by 9
  16. 2023Discrete Latent Structure in Neural Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 0; 2026: 3.

8 papers.

  1. 2024Graph Neural Networks for Virtual Sensing in Complex Systems: Addressing Heterogeneous Temporal Dynamicscited by 7
  2. 2024Physics-Enhanced Graph Neural Networks For Soft Sensing in Industrial Internet of Thingscited by 6
  3. 2024Joint Estimation and Prediction of City-wide Delivery Demand: A Large Language Model Empowered Graph-based Learning Approachcited by 6
  4. 2024Learning Latent Graph Structures and their Uncertaintycited by 4
  5. 2026Why Do Time Series Models Need Long Context Windows?cited by 2
  6. 2024On the Regularization of Learnable Embeddings for Time Series Forecastingcited by 1
  7. 2026Interpretability in Deep Time Series Models Demands Semantic Alignmentcited by 0
  8. 2026A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal Graphcited by 0