Conformal Load Prediction with Transductive Graph Autoencoders
This work addresses the problem of reliable edge weight prediction for applications like transportation systems, though it is incremental as it builds on existing conformal prediction and GNN methods.
The paper tackled edge weight prediction on graphs by developing a Graph Neural Network approach with conformal prediction to ensure guaranteed coverage, resulting in better coverage and efficiency than baselines on real-world transportation datasets.
Predicting edge weights on graphs has various applications, from transportation systems to social networks. This paper describes a Graph Neural Network (GNN) approach for edge weight prediction with guaranteed coverage. We leverage conformal prediction to calibrate the GNN outputs and produce valid prediction intervals. We handle data heteroscedasticity through error reweighting and Conformalized Quantile Regression (CQR). We compare the performance of our method against baseline techniques on real-world transportation datasets. Our approach has better coverage and efficiency than all baselines and showcases robustness and adaptability.