mlsanityData to 14 Oct 2026

GEM-FI: Gated Evidential Mixtures with Fisher Modulation

arXiv 2605.03750 ↗First posted 5 May 2026cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Evidential Deep Learning (EDL) enables single-pass uncertainty estimation by predicting Dirichlet evidence, but it can remain overconfident and poorly calibrated, and it often fails to represent multi-modal epistemic uncertainty. We introduce Gated Evidential Mixtures (GEM), a family of models that learns an in-model energy signal and uses it to gate evidential outputs end-to-end in a distance-informed manner. GEM-CORE learns a feature-level energy and maps it to a bounded gate that smoothly suppresses evidence when support is low. To capture epistemic multi-modality without multi-pass ensembling, GEM-MIX adds a lightweight mixture of evidential heads with learned routing weights while preserving single-pass inference. Finally, GEM-FI stabilizes mixture allocations via a Fisher-informed regularizer, reducing head collapse and producing smoother boundary uncertainty. Across image classification and OOD detection benchmarks, GEM improves calibration and ID/OOD separation with single-pass inference. On CIFAR-10, GEM-FI vs. DAEDL improves accuracy from 91.11 to 93.75 (+2.64 pp), reduces Brier x100 from 14.27 to 6.81 (-7.46), and also improves misclassification-detection AUPR from 99.08 to 99.94 (+0.86). For epistemic OOD detection, GEM-FI achieves AUPR/AUROC of 92.59/95.09 on CIFAR-10 to SVHN and 90.20/89.06 on CIFAR-10 to CIFAR-100, compared with 85.54/89.30 and 88.19/86.10 for DAEDL.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 20 of its 41 references that are in the map. First posted on arXiv 5 May 2026.

Builds on

20 of 41 references.

References · 20

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  9. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  10. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  11. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  12. 2015Weight Uncertainty in Neural Networkscited by 554
8 more
  1. 2018Deep Learning for Classical Japanese Literaturecited by 422
  2. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  3. 2021Revisiting the Calibration of Modern Neural Networkscited by 390
  4. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 293
  5. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 138
  6. 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
  7. 2024Uncertainty Estimation by Density Aware Evidential Deep Learningcited by 22
  8. 2024Revisiting Essential and Nonessential Settings of Evidential Deep Learningcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Estimating Uncertainty in Galaxy Morphology Classificationcited by 0