analiza aiqbench
This research introduces ORCU, the first loss function designed to simultaneously enforce calibration and unimodality in ordinal classification tasks without altering network architecture or requiring post-hoc adjustments. By theoretically coupling distance-aware soft encoding with log-barrier extensions on adjacent logits, it resolves a longstanding gap where prior methods prioritized order consistency at the expense of prediction reliability. The work establishes a new benchmark for trustworthy machine learning systems handling ranked data across four specialized domains.
Ordinal-Aware Calibration for Ordinal Classification
arXiv:2410.15658v4 Announce Type: replace Abstract: Deep neural networks frequently produce overconfident, miscalibrated predictions. In ordinal classification, predictions must also adhere to a unimodal and order-consistent structure, a requirement that has dominated prior work while overlooking calibration. We formalize this joint challenge as ordinal calibration for the first time and propose the Ordinal loss for Calibration and Unimodality (ORCU). Unlike incremental modular combinations, ORCU provides a concise, principled unification of distance-aware soft encoding and an ordinal-aware log-barrier extension on adjacent logit gaps. This coupling is theoretically synergetic: soft-encoded targets pre-condition the optimization landscape by providing a finite, full-support ordinal anchor for well-posed refinement, while the log-barrier extension preserves non-vanishing adjacent-gap gradients in the unimodality-feasible interior. This enables the log-barrier to refine confidence without disrupting the ordinal geometry. ORCU requires no architectural changes or post-hoc calibration. Across four ordinal benchmarks, it achieves state-of-the-art calibration without compromising accuracy. We establish a new reliability standard by providing a reproducible benchmark over 10 specialized and general-purpose loss functions. Our code is available at https://github.com/labhai/ORCU.
Abstract:Deep neural networks frequently produce overconfident, miscalibrated predictions. In ordinal classification, predictions must also adhere to a unimodal and order-consistent structure, a requirement that has dominated prior work while overlooking calibration. We formalize this joint challenge as ordinal calibration for the first time and propose the Ordinal loss for Calibration and Unimodality (ORCU). Unlike incremental modular combinations, ORCU provides a concise, principled unification of distance-aware soft encoding and an ordinal-aware log-barrier extension on adjacent logit gaps. This coupling is theoretically synergetic: soft-encoded targets pre-condition the optimization landscape by providing a finite, full-support ordinal anchor for well-posed refinement, while the log-barrier extension preserves non-vanishing adjacent-gap gradients in the unimodality-feasible interior. This enables the log-barrier to refine confidence without disrupting the ordinal geometry. ORCU requires no architectural changes or post-hoc calibration. Across four ordinal benchmarks, it achieves state-of-the-art calibration without compromising accuracy. We establish a new reliability standard by providing a reproducible benchmark over 10 specialized and general-purpose loss functions. Our code is available at this https URL.
Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2410.15658 [cs.LG]
(or arXiv:2410.15658v4 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2410.15658 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 264 cuvinte
Subiecte conexe
A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs
arXiv · 7 sept. 2026
HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration
arXiv · 30 sept. 2026
Inference-Time Decision Calibration for Temporal Classification
arXiv · 16 iun. 2026
SafeECGMatch: Calibration-Aware Joint Frequency and Time Space Semi-Supervised Learning for Open-Set ECG Classification
arXiv · 31 iul. 2026