2024/11/19 by Nan Ye, Ye, Nai-Xuan, Tan-Ha Mai +7 · 1 citation
Computer Science · #Computer graphics (images) #Computer science #Natural Language Processing Techniques #Programming language #Python (programming language) #Video Analysis and Summarization
paper · pdf · doi:10.48550/arxiv.2411.12276
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/11/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Complementary-label learning (CLL) is a weakly supervised learning paradigm for multiclass classification, where only complementary labels -- indicating classes an instance does not belong to -- are provided to the learning algorithm. Despite CLL's increasing popularity, previous studies highlight two main challenges: (1) inconsistent results arising from varied assumptions on complementary label generation, and (2) high barriers to entry due to the lack of a standardized evaluation platform across datasets and algorithms. To address these challenges, we introduce libcll, an extensible Python toolkit for CLL research. libcll provides a universal interface that supports a wide range of generation assumptions, both synthetic and real-world datasets, and key CLL algorithms. The toolkit is designed to mitigate inconsistencies and streamline the research process, with easy installation, comprehensive usage guides, and quickstart tutorials that facilitate efficient adoption and implementation of CLL techniques. Extensive ablation studies conducted with libcll demonstrate its utility in generating valuable insights to advance future CLL research.