SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.02354 · 2024

Label-wise Aleatoric and Epistemic Uncertainty Quantification

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 11 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
YSale/label-uq canonical 11 of 14
FunctionStatusWhere it lives
accuracy Ran YSale/label-uq/arc_ood/utils.py
pointer only (licence: GPL-3.0) · get_code("ef6da3c8f8497e94")
aleatoric_uncertainty_variance Ran YSale/label-uq/holdout/unc_label.py
pointer only (licence: GPL-3.0) · get_code("f3921a2f331761fa")
aleatoric_uncertainty_variance Ran YSale/label-uq/arc_ood/uncertainty.py
pointer only (licence: GPL-3.0) · get_code("4d542a15c47ad321")
append_array Ran YSale/label-uq/arc_ood/utils.py
pointer only (licence: GPL-3.0) · get_code("1481be59d3acc642")
epistemic_uncertainty_variance Ran YSale/label-uq/holdout/unc_label.py
pointer only (licence: GPL-3.0) · get_code("f96930278eed1ed5")
epistemic_uncertainty_variance Ran YSale/label-uq/arc_ood/uncertainty.py
pointer only (licence: GPL-3.0) · get_code("49995991be7d33fc")
get_data Ran YSale/label-uq/arc_ood/data.py
pointer only (licence: GPL-3.0) · get_code("ebe31a9076be0d2b")
get_data Ran YSale/label-uq/holdout/data.py
pointer only (licence: GPL-3.0) · get_code("baf5a792dc1a4a95")
get_probs Ran YSale/label-uq/holdout/data.py
pointer only (licence: GPL-3.0) · get_code("259d23a3b6e83ce7")
total_uncertainty_variance Ran YSale/label-uq/holdout/unc_label.py
pointer only (licence: GPL-3.0) · get_code("cf3dab7fb4f63630")
total_uncertainty_variance Ran YSale/label-uq/arc_ood/uncertainty.py
pointer only (licence: GPL-3.0) · get_code("9b5cd0c059dd3261")
get_resnet50 Not yet run YSale/label-uq/medical/models.py
pointer only (licence: GPL-3.0) · get_code("4fd78ff184dad0c4")
torch_get_outputs Not yet run YSale/label-uq/arc_ood/utils.py
pointer only (licence: GPL-3.0) · get_code("325291a8a89d7777")
train_ensemble Not yet run YSale/label-uq/holdout/holdout.py
pointer only (licence: GPL-3.0) · get_code("2b9efd66fa8cd036")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of uncertainty measures. This label-wise perspective allows uncertainty to be quantified at the individual class level, thereby improving cost-sensitive decision-making and helping understand the sources of uncertainty. Furthermore, it allows to define total, aleatoric, and epistemic uncertainty on the basis of non-categorical measures such as variance, going beyond common entropy-based measures. In particular, variance-based measures address some of the limitations associated with established methods that have recently been discussed in the literature. We show that our proposed measures adhere to a number of desirable properties. Through empirical evaluation on a variety of benchmark data sets -- including applications in the medical domain where accurate uncertainty quantification is crucial -- we establish the effectiveness of label-wise uncertainty quantification.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.02354")
get_code_for_paper("2406.02354")
have("2406.02354")

Connect an agent — have() is free.