Multi-Label Learning With Multiple Complementary Labels

Yi Gao

doi:10.1109/TPAMI.2025.3574183

Return

Multi-Label Learning With Multiple Complementary Labels

2025-09-01

PRE

DOI：10.1109/TPAMI.2025.3574183

Original

Original request for help

Save

Abstract

En 中文

In multi-labeled complementary label learning (MLCLL), a complementary label (CL) represents an irrelevant label for an instance. Utilizing CLs instead of relevant labels as annotations simplifies the annotation process in multi-label learning (MLL) tasks, underscoring the practicality of the MLCLL problem. However, existing MLCLL approaches mainly focus on scenarios where an instance is associated with a single CL. This restricts their applicability in situations where annotators provide multiple CLs per instance. To address this limitation, we propose a novel paradigm called multi-label learning with multiple complementary labels (ML-MCL), which allows each instance to be associated with multiple CLs simultaneously. Through analyzing the generation process of multiple CLs, we construct the relationship between relevant labels and CLs. This assists in deriving a tailored risk-consistent estimator to solve MLCLL with multiple CLs. Theoretically, we establish an estimation error bound for this estimator, with a convergence rate of $\mathcal {O}(1/\sqrt{n})$. Furthermore, we observed that unbounded gradients can be produced in the derived estimator when optimizing with certain loss functions, which may lead to unstable optimization. To mitigate this issue, we enhance the estimator with a confidence truncation loss, stabilizing the optimization process. Experimental results confirm the effectiveness of our approach, showing improved learning stability and performance in MLCLL tasks involving multiple CLs.

Keywords:

Complementary label learning

multi-label learning

risk-consistent estimator

estimation error bound