DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917544487550976 |
|---|---|
| author | Lee, Hyuck Park, Taemin Kim, Heeyoung |
| author_facet | Lee, Hyuck Park, Taemin Kim, Heeyoung |
| contents | Various algorithms have been proposed to address the challenges posed by class-imbalanced learning from real-world data with long-tailed distributions. While these algorithms reduce prediction bias through rebalancing techniques, they often introduce increased prediction variance as a trade-off. Several multi-expert learning algorithms aim to address this variance but involve complex procedures. We propose a new multi-expert learning algorithm, called the dual-axis multi-expert learning (DAMEL), which reduces both bias and variance of predictions by using multiple experts along both representation and time axes. Along the representation axis, DAMEL concatenates the representations of multiple experts and trains an auxiliary balanced classifier simultaneously with the concatenated representations. Along the time axis, DAMEL aggregates network weights across training epochs, employing these aggregated weights during testing. Experimental results demonstrate that DAMEL reduces both bias and variance of predictions, highlighting its effectiveness in class-imbalanced learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30135 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning Lee, Hyuck Park, Taemin Kim, Heeyoung Machine Learning Artificial Intelligence Various algorithms have been proposed to address the challenges posed by class-imbalanced learning from real-world data with long-tailed distributions. While these algorithms reduce prediction bias through rebalancing techniques, they often introduce increased prediction variance as a trade-off. Several multi-expert learning algorithms aim to address this variance but involve complex procedures. We propose a new multi-expert learning algorithm, called the dual-axis multi-expert learning (DAMEL), which reduces both bias and variance of predictions by using multiple experts along both representation and time axes. Along the representation axis, DAMEL concatenates the representations of multiple experts and trains an auxiliary balanced classifier simultaneously with the concatenated representations. Along the time axis, DAMEL aggregates network weights across training epochs, employing these aggregated weights during testing. Experimental results demonstrate that DAMEL reduces both bias and variance of predictions, highlighting its effectiveness in class-imbalanced learning. |
| title | DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.30135 |