cs.LGFeb 18, 2025

Fragility-aware Classification for Risk Characterization and Robust Learning

Authors: Zheng Cui, Daniel Zhuoyu Long, Jin Qi, Chen Yang, Ruohan Zhan

Organizations: School of Management, Zhejiang University · Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong · Department of Industrial Engineering and Decision Analytics, Hong Kong University of Science and Technology · Department of Marketing and Analytics, University College London

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Classification models play a central role in data-driven decision-making applications such as medical diagnosis, recommendation systems, and risk assessment. Traditional performance metrics, such as accuracy and AUC, quantify classification errors and pairwise ranking performance but do not account for the magnitude of errors, i.e., the risk of confident misjudgments. This limitation is particularly consequential in safety-critical and cost-sensitive settings, where overconfident errors can lead to severe outcomes. To address this issue, we propose the Fragility Index (FI), a novel performance metric that evaluates classifiers from a risk-averse perspective by capturing the tail risk of confident misjudgments. We formulate FI within a robust satisficing (RS) framework to quantify classifier sensitivity under distributional uncertainty. Building on this, we develop a tractable surrogate-based training framework and establish provable bounds connecting training fragility to ranking-error FI. We further derive tractable reformulations for a broad class of loss functions, including cross-entropy, hinge-type, and Lipschitz losses, and identify specific conditions under which these reformulations are exact. We also introduce an FI-induced regularizer for deep neural networks. Empirical results on real-world medical diagnosis tasks demonstrate that FI complements existing metrics by revealing error tail risk not reflected in accuracy or AUC. FI-based models achieve competitive predictive performance while generally attaining lower FI. In the simulated human--AI diagnostic workflow, they also achieve lower average operational costs than empirical risk minimization.

More in this topic

Robust Classification

See all 39 papers

Explore similar work

CardsList
Feb 24, 2026

Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions

In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance involves a benign or safety-critical class. We decompose MI into a per-class vector Ck(x)=σk2/(2μk)C_k(x)=σ_k^{2}/(2μ_k), with μk=E[pk]μ_k{=}\mathbb{E}[p_k] and σk2=Var[pk]σ_k^2{=}\mathrm{Var}[p_k] across posterior samples. The decomposition follows from a second-order Taylor expansion of the entropy; the 1/μk1/μ_k weighting corrects boundary suppression and makes CkC_k comparable across rare and common classes. By construction ∑kCk≈MI\sum_k C_k \approx \mathrm{MI}, and a companion skewness diagnostic flags inputs where the approximation degrades. After characterising the axiomatic properties of CkC_k, we validate it on three tasks: (i) selective prediction for diabetic retinopathy, where critical-class CkC_k reduces selective risk by 34.7% over MI and 56.2% over variance baselines; (ii) out-of-distribution detection on clinical and image benchmarks, where ∑kCk\sum_k C_k achieves the highest AUROC and the per-class view exposes asymmetric shifts invisible to MI; and (iii) a controlled label-noise study in which ∑kCk\sum_k C_k shows less sensitivity to injected aleatoric noise than MI under end-to-end Bayesian training, while both metrics degrade under transfer learning. Across all tasks, the quality of the posterior approximation shapes uncertainty at least as strongly as the choice of metric, suggesting that how uncertainty is propagated through the network matters as much as how it is measured.

Mame Diarra Toure, David A. Stephens

Department of Mathematics and Statistics , McGill University

Bayesian Neural NetworksClassificationMutual Information EstimationUncertainty DecompositionEpistemic Uncertainty
AskPDF
Aug 10, 2026

ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning

A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken. Empirical risk minimization (ERM) controls average loss but not this failure directly, while calibration, uncertainty estimation, conformal risk control, and selective prediction methods target related reliability properties rather than bounding the joint failure event during training. We propose ReliableNet, which constrains the Joint Confident-Wrong (JCW) probability, the probability that a prediction is simultaneously confident and incorrect, below a user-specified risk budget α∈(0,1)α\in(0,1). We formulate this as a chance-constrained ERM problem, use a conservative smooth inner approximation whose population feasibility implies the original JCW constraint. Across four tabular and two image datasets, ReliableNet is the only method certified within the JCW budget for every dataset and seed in distribution, when compared against baselines spanning ERM, post-hoc calibration, conformal risk control, and selective prediction. Under demographic, ambiguity, spurious-correlation, novel-class, and covariate shifts, it achieves the lowest empirical JCW among the compared methods while remaining very competitive in accuracy, coverage, calibration, and selective prediction. Risk-coverage results further indicate that ReliableNet achieves better selective ranking than the benchmark methods on most datasets. Overall, ReliableNet provides a principled approach to trustworthy classification.

Ange-Clément Akazan, Ineza Remy Mugenga, Abebe Geletu +2

School of Agriculture and Science, University of KwaZulu-Natal, Pietermaritzburg, KwaZulu-Natal, South Africa · 2AIMS Research and Innovation Centre, African Institute for Mathematical Sciences, Kigali, Rwanda · 3African Institute for Mathematical Sciences, Kigali, Rwanda

Chance-Constrained OptimizationClassificationEmpirical Risk Minimization
AskPDF
May 9, 2026

FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness

Robust adaptation of LLMs and VLMs is often evaluated by average accuracy or average consistency under perturbations. However, these averages can hide a structured failure mode: a prediction may remain correct while probability mass already flows from particular true classes toward systematic wrong competitors near the decision boundary. In this paper, we formalize this phenomenon as margin-aware error flow and introduce FragileFlow, a plug-in regularizer that uses a calibrated margin buffer to identify correct-but-fragile predictions and organize their off-class probability mass into a class-wise vulnerable-risk matrix. Theoretically, we provide the first PAC-Bayes upper bound for this margin-aware error-flow object, showing how empirical spectral control yields a conservative route to deterministic worst-class robustness under a stability condition. Experiments on multiple-choice LLM benchmarks and few-shot CLIP adaptation show that FragileFlow consistently improves the proposed theory-facing risk measures over matched baselines, yields perturbed worst-class accuracy gains in most settings, and preserves clean accuracy across comparisons.

Zhuoyun Li, Boxuan Wang, Jinwei Hu +2

School of Computer Science and Informatics, University of Liverpool, UK

VLM RobustnessSpectral RegularizationVLM AdaptationNeural Network RobustnessAdversarial RobustnessLanguage Model Robustness
AskPDF