Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914120313339904 |
|---|---|
| author | Zhang, Kuan Chai, Chengliang Xu, Jingzhe Zhang, Chi Han, Han Yuan, Ye Wang, Guoren Cao, Lei |
| author_facet | Zhang, Kuan Chai, Chengliang Xu, Jingzhe Zhang, Chi Han, Han Yuan, Ye Wang, Guoren Cao, Lei |
| contents | Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational costs, heavy hyperparameter tuning process, and coarse-grained optimization. To address these challenges, we propose a novel two-stage noisy learning framework that enables instance-level optimization through a dynamically weighted loss function, avoiding hyperparameter tuning. To obtain stable and accurate information about noise modeling, we introduce a simple yet effective metric, termed wrong event, which dynamically models the cleanliness and difficulty of individual samples while maintaining computational costs. Our framework first collects wrong event information and builds a strong base model. Then we perform noise-robust training on the base model, using a probabilistic model to handle the wrong event information of samples. Experiments on five synthetic and real-world LNL benchmarks demonstrate our method surpasses state-of-the-art methods in performance, achieves a nearly 75% reduction in computational time and improves model scalability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00812 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization Zhang, Kuan Chai, Chengliang Xu, Jingzhe Zhang, Chi Han, Han Yuan, Ye Wang, Guoren Cao, Lei Machine Learning Artificial Intelligence Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational costs, heavy hyperparameter tuning process, and coarse-grained optimization. To address these challenges, we propose a novel two-stage noisy learning framework that enables instance-level optimization through a dynamically weighted loss function, avoiding hyperparameter tuning. To obtain stable and accurate information about noise modeling, we introduce a simple yet effective metric, termed wrong event, which dynamically models the cleanliness and difficulty of individual samples while maintaining computational costs. Our framework first collects wrong event information and builds a strong base model. Then we perform noise-robust training on the base model, using a probabilistic model to handle the wrong event information of samples. Experiments on five synthetic and real-world LNL benchmarks demonstrate our method surpasses state-of-the-art methods in performance, achieves a nearly 75% reduction in computational time and improves model scalability. |
| title | Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.00812 |