%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:19:08 PM

@ARTICLE{Pannatier_TMLR_2024,
         author = {Pannatier, Arnaud and Matoba, Kyle and Fleuret, Francois},
       projects = {MALAT},
          month = apr,
          title = {Inference from Real-World Sparse Measurements},
        journal = {TMLR},
      booktitle = {Transactions on Machine Learning Research},
           year = {2024},
       abstract = {Real-world problems often involve complex and unstructured sets of measurements, which occur when sensors are sparsely placed in either space or time. Being able to model this irregular spatiotemporal data and extract meaningful forecasts is crucial. Deep learning architectures capable of processing sets of measurements with positions varying from set to set, and extracting readouts anywhere are methodologically difficult. Current state-of-the-art models are graph neural networks and require domain-specific knowledge for proper setup.

  We propose an attention-based model focused on robustness and practical applicability, with two key design contributions. First, we adopt a ViT-like transformer that takes both context points and read-out positions as inputs, eliminating the need for an encoder-decoder structure. Second, we use a unified method for encoding both context and read-out positions. This approach is intentionally straightforward and integrates well with other systems. Compared to existing approaches, our model is simpler, requires less specialized knowledge, and does not suffer from a problematic bottleneck effect, all of which contribute to superior performance.

  We conduct in-depth ablation studies that characterize this problematic bottleneck in the latent representations of alternative models that inhibit information utilization and impede training efficiency. We also perform experiments across various problem domains, including high-altitude wind nowcasting, two-day weather forecasting, fluid dynamics, and heat diffusion. Our attention-based model consistently outperforms state-of-the-art models in handling irregularly sampled data. Notably, our model reduces the root mean square error (RMSE) for wind nowcasting from 9.24 to 7.98 and for heat diffusion tasks from 0.126 to 0.084.},
            pdf = {https://publications.idiap.ch/attachments/papers/2024/Pannatier_TMLR_2024.pdf}
}