Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2411.12724 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909465001852928 |
|---|---|
| author | Nguyen, Huy Thong Chu, En-Hung Melvix, Lenord Jiao, Jazon Wen, Chunglin Louie, Benjamin |
| author_facet | Nguyen, Huy Thong Chu, En-Hung Melvix, Lenord Jiao, Jazon Wen, Chunglin Louie, Benjamin |
| contents | We introduce Teacher2Task, a novel framework for multi-teacher learning that eliminates the need for manual aggregation heuristics. Existing multi-teacher methods typically rely on such heuristics to combine predictions from multiple teachers, often resulting in sub-optimal aggregated labels and the propagation of aggregation errors. Teacher2Task addresses these limitations by introducing teacher-specific input tokens and reformulating the training process. Instead of relying on aggregated labels, the framework transforms the training data, consisting of ground truth labels and annotations from N teachers, into N+1 distinct tasks: N auxiliary tasks that predict the labeling styles of the N individual teachers, and one primary task that focuses on the ground truth labels. This approach, drawing upon principles from multiple learning paradigms, demonstrates strong empirical results across a range of architectures, modalities, and tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_12724 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Heuristic-Free Multi-Teacher Learning Nguyen, Huy Thong Chu, En-Hung Melvix, Lenord Jiao, Jazon Wen, Chunglin Louie, Benjamin Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition We introduce Teacher2Task, a novel framework for multi-teacher learning that eliminates the need for manual aggregation heuristics. Existing multi-teacher methods typically rely on such heuristics to combine predictions from multiple teachers, often resulting in sub-optimal aggregated labels and the propagation of aggregation errors. Teacher2Task addresses these limitations by introducing teacher-specific input tokens and reformulating the training process. Instead of relying on aggregated labels, the framework transforms the training data, consisting of ground truth labels and annotations from N teachers, into N+1 distinct tasks: N auxiliary tasks that predict the labeling styles of the N individual teachers, and one primary task that focuses on the ground truth labels. This approach, drawing upon principles from multiple learning paradigms, demonstrates strong empirical results across a range of architectures, modalities, and tasks. |
| title | Heuristic-Free Multi-Teacher Learning |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.12724 |