Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations

Authors: Giovanni De Felice, Andrea Cini, Daniele Zambon, Vladimir Gusev, Cesare Alippi

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental we carry out an extensive empirical evaluation by exploring different use cases and assessing the performance of the proposed method against the state-of-the-art (Sec. 5).
Researcher Affiliation Academia Giovanni De Felice1 , Andrea Cini2, Daniele Zambon2, Vladimir V. Gusev1, Cesare Alippi2,3 1University of Liverpool 2The Swiss AI Lab IDSIA & Universit a della Svizzera italiana 3Politecnico di Milano
Pseudocode No The paper describes its methodology and architecture in detail but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes Python code to reproduce the experiments is available online at https://github.com/ gdefe/ggnet-virtual-sensing.
Open Datasets Yes Complete climatic and photovoltaic datasets are publicly available online through the references provided in Appendix D.
Dataset Splits Yes Among all N D channels, we use 70% for training, 10% for validation, and the remaining 20% for testing.
Hardware Specification Yes Timings are taken on a machine equipped with an NVIDIA A100 GPU.
Software Dependencies No The paper mentions 'Python' and 'Torch Spatiotemporal' but does not specify version numbers for these or any other software components.
Experiment Setup Yes For Gg Net and all baselines, we adopt the Adam optimizer (Kingma & Ba, 2015) with a learning rate lr = 0.001 paired with a cosine annealing learning rate scheduler. All models are trained for a maximum of 500 epochs, with a 30 epochs patience for early stopping. All batches have a size set to 32 and consider temporal windows of tw = 24 time steps.