MaxEnt Loss: Calibrating Graph Neural Networks Under Out-of-Distribution Shift (Student Abstract)

AAAI 2024 pp. 23594-23596

doi:10.1609/AAAI.V38I21.30487 /aaai/2024/neo2024aaai-maxent-a/

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.

PDF AAAI Semantic Scholar

Cite

Text

Neo. "MaxEnt Loss: Calibrating Graph Neural Networks Under Out-of-Distribution Shift (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30487

Markdown

[Neo. "MaxEnt Loss: Calibrating Graph Neural Networks Under Out-of-Distribution Shift (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/neo2024aaai-maxent-a/) doi:10.1609/AAAI.V38I21.30487

BibTeX

@inproceedings{neo2024aaai-maxent-a,
  title     = {{MaxEnt Loss: Calibrating Graph Neural Networks Under Out-of-Distribution Shift (Student Abstract)}},
  author    = {Neo, Dexter},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23594-23596},
  doi       = {10.1609/AAAI.V38I21.30487},
  url       = {https://mlanthology.org/aaai/2024/neo2024aaai-maxent-a/}
}