Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning

arXiv:2506.05937 · cs.LG, cs.AI · Submitted 2025-06-06 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-06-06

Updated: 2026-10-02

Code: https://github.com/team-daniel/cedl

Terminology

• Uncertainty Quantification — 2× in this paper · explained in 9 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• GPT-4 Technical Report
• Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
• Deep Learning for Classical Japanese Literature
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Adam: A Method for Stochastic Optimization
• Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
• Foolbox: A Python toolbox to benchmark the robustness of machine learning models
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Uncertainty Estimation by Density Aware Evidential Deep Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks