From the 1 of 5 linked papers with an AI index.
5 papers
Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus
Rasmus Tirsgaard, Laurits Fredsgaard, Marisa Wodrich +2
The paper proposes a semi-supervised learning approach for molecular graph data that uses an ensemble consensus objective to improve prediction accuracy, robustness, and calibratio…
Same Graph, Different Likelihoods: Calibration of Autoregressive Graph Generators via Permutation-Equivalent Encodings
Laurits Fredsgaard, Aaron Thomas, Michael Riis Andersen +2
Autoregressive graph generators define likelihoods via a sequential construction process, but these likelihoods are only meaningful if they are consistent across all linearizations…
Practical Deep Heteroskedastic Regression
Mikkel Jordahn, Jonas Vestergaard Jensen, James Harrison +2
Uncertainty quantification (UQ) in deep learning regression is of wide interest, as it supports critical applications including sequential decision making and risk-sensitive tasks.…
On Joint Regularization and Calibration in Deep Ensembles
Laurits Fredsgaard, Mikkel N. Schmidt
Deep ensembles are a powerful tool in machine learning, improving both model performance and uncertainty calibration. While ensembles are typically formed by training and tuning mo…
On Local Posterior Structure in Deep Ensembles
Mikkel Jordahn, Jonas Vestergaard Jensen, Mikkel N. Schmidt +1
Bayesian Neural Networks (BNNs) often improve model calibration and predictive uncertainty quantification compared to point estimators such as maximum-a-posteriori (MAP). Similarly…