Spatial Graph Coarsening: Weather and Weekday Prediction with London's Bike-Sharing Service using GNN
This work addresses a domain-specific problem for urban planning or bike-sharing services, but it is incremental as it builds on existing GNN methods.
The study tackled predicting weather and weekday from London's bike-sharing data using a Graph Neural Network (GNN) with new operators, achieving improved cross-entropy loss and accuracy over a baseline.
This study introduced the use of Graph Neural Network (GNN) for predicting the weather and weekday of a day in London, from the dataset of Santander Cycles bike-sharing system as a graph classification task. The proposed GNN models newly introduced (i) a concatenation operator of graph features with trained node embeddings and (ii) a graph coarsening operator based on geographical contiguity, namely "Spatial Graph Coarsening". With the node features of land-use characteristics and number of households around the bike stations and graph features of temperatures in the city, our proposed models outperformed the baseline model in cross-entropy loss and accuracy of the validation dataset.