Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mai, Tan-Ha, Chiang, Chao-Kai, Shih, Han-Hwa, Niu, Gang, Sugiyama, Masashi, Lin, Hsuan-Tien
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918508955172864
author Mai, Tan-Ha
Chiang, Chao-Kai
Shih, Han-Hwa
Niu, Gang
Sugiyama, Masashi
Lin, Hsuan-Tien
author_facet Mai, Tan-Ha
Chiang, Chao-Kai
Shih, Han-Hwa
Niu, Gang
Sugiyama, Masashi
Lin, Hsuan-Tien
contents Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling to large label spaces continuing to be an enduring bottleneck. This limitation stems from the common assumption of uniform label generation in traditional methods, which fatally dilutes the learning signal in many-class settings. In this paper, we demonstrate that this long-standing barrier can be overcome by deliberately designing a biased (non-uniform) generation process that restricts complementary labels to a subset of classes. This finding motivates us to propose Bias-Induced Constrained Labeling (BICL), a principled framework spanning data collection to training that leverages this bias. BICL enables effective learning on CIFAR-100 and TinyImageNet-200, achieving more than sevenfold accuracy improvements over traditional methods. Our findings establish a new trajectory for making CLL feasible for many classes in real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15586
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes
Mai, Tan-Ha
Chiang, Chao-Kai
Shih, Han-Hwa
Niu, Gang
Sugiyama, Masashi
Lin, Hsuan-Tien
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling to large label spaces continuing to be an enduring bottleneck. This limitation stems from the common assumption of uniform label generation in traditional methods, which fatally dilutes the learning signal in many-class settings. In this paper, we demonstrate that this long-standing barrier can be overcome by deliberately designing a biased (non-uniform) generation process that restricts complementary labels to a subset of classes. This finding motivates us to propose Bias-Induced Constrained Labeling (BICL), a principled framework spanning data collection to training that leverages this bias. BICL enables effective learning on CIFAR-100 and TinyImageNet-200, achieving more than sevenfold accuracy improvements over traditional methods. Our findings establish a new trajectory for making CLL feasible for many classes in real-world applications.
title Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.15586