Metraipolis › archive › dc_ee7cf2a8f8a0
Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification — arXiv:2609.10752
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10752
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:24:39.727Z
- SHA-256 of the archived text
645e7ef24b451072c508927738576c72b3b75ea98bf670101a238d436fe3985f- Stable URL of this page
https://metraipolis.com/documento/dc_ee7cf2a8f8a0
How to cite
Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification — arXiv:2609.10752 — arXiv (en), https://arxiv.org/abs/2609.10752 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee7cf2a8f8a0 (Metraipolis archive dc_ee7cf2a8f8a0, sha256 645e7ef24b451072c508927738576c72b3b75ea98bf670101a238d436fe3985f)
BibTeX
@misc{dcee7cf2a8f8a0,
title = {Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification — arXiv:2609.10752},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10752},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee7cf2a8f8a0; sha256 645e7ef24b451072c508927738576c72b3b75ea98bf670101a238d436fe3985f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10752. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Standard cross-entropy loss causes neural networks trained on ordinal classification tasks to hedge predictions toward center classes, a failure mode we term \emph{center-class hedging}. This occurs because predicting the middle class minimizes expected symmetric loss, making it the path of least resistance regardless of the true label. Existing ordinal losses address related problems such as large-error penalization and rank consistency, but none directly suppresses center-class hedging as a function of where the true label lies relative to the ordinal center. We propose the Adaptive Margin Ordinal Loss (AMOL), a multiplicative weight applied to per-class loss terms of the form $m(k,y) = 1 + \alpha \cdot (1 - |k-c|/c) \cdot (|y-c|/c)$, where $c$ is the center class, $k$ is the candidate class, and $y$ is the true label. The weight encodes a joint condition: it is large only when the candidate class is near center and the true label is far from center, collapsing to standard behavior otherwise. We further introduce the Center-Hedging Rate (CHR) as a diagnostic metric that directly quantifies this failure mode. Across four ordinal classification benchmarks and five random seeds, AMOL achieves the best or tied-best Quadratic Weighted Kappa (QWK) on all four datasets compared to cross-entropy, OLL, and SORD baselines. An asymmetric variant (AMOL-asym) eliminates center-class hedging entirely on the Abalone dataset ($\text{CHR} = 0.000 \pm 0.000$ across all five seeds, $n \approx 266$ extreme-class test samples per run), compared to $0.074 \pm 0.005$ for standard cross-entropy.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.10752 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:17:52.080Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).