AAAI 2024technical0 citations
MaxEnt Loss: Calibrating Graph Neural Networks under Out-of-Distribution Shift (Student Abstract)
Abstract
We present a new, simple and effective loss function for calibrating graph neural networks (GNNs). Miscalibration is the problem whereby a model's probabilities does not reflect it's correctness, making it difficult and possibly dangerous for real-world deployment. We compare our method against other baselines on a novel ID and OOD graph form of the Celeb-A faces dataset. Our findings show that our method improves calibration for GNNs, which are not immune to miscalibration in-distribution (ID) and out-of-distribution (OOD). Our code is available for review at https://github.com/dexterdley/CS6208/tree/main/Project.
BibTeX
@article{Neo_2024, title={MaxEnt Loss: Calibrating Graph Neural Networks under Out-of-Distribution Shift (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30487}, DOI={10.1609/aaai.v38i21.30487}, abstractNote={We present a new, simple and effective loss function for calibrating graph neural networks (GNNs). Miscalibration is the problem whereby a model’s probabilities does not reflect it’s correctness, making it difficult and possibly dangerous for real-world deployment. We compare our method against other baselines on a novel ID and OOD graph form of the Celeb-A faces dataset. Our findings show that our method improves calibration for GNNs, which are not immune to miscalibration in-distribution (ID) and out-of-distribution (OOD). Our code is available for review at https://github.com/dexterdley/CS6208/tree/main/Project.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Neo, Dexter}, year={2024}, month={Mar.}, pages={23594-23596} }