CoGraM: Context-sensitive granular optimization method with rollback for robust model fusion
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911306008756224 |
|---|---|
| author | Lenz, Julius |
| author_facet | Lenz, Julius |
| contents | Merging neural networks without retraining is central to federated and distributed learning. Common methods such as weight averaging or Fisher merging often lose accuracy and are unstable across seeds. CoGraM (Contextual Granular Merging) is a multi-stage, context-sensitive, loss-based, and iterative optimization method across layers, neurons, and weight levels that aligns decisions with loss differences and thresholds and prevents harmful updates through rollback. CoGraM is an optimization method that addresses the weaknesses of methods such as Fisher and can significantly improve the merged network. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03610 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoGraM: Context-sensitive granular optimization method with rollback for robust model fusion Lenz, Julius Machine Learning I.2.6; F.2.0 Merging neural networks without retraining is central to federated and distributed learning. Common methods such as weight averaging or Fisher merging often lose accuracy and are unstable across seeds. CoGraM (Contextual Granular Merging) is a multi-stage, context-sensitive, loss-based, and iterative optimization method across layers, neurons, and weight levels that aligns decisions with loss differences and thresholds and prevents harmful updates through rollback. CoGraM is an optimization method that addresses the weaknesses of methods such as Fisher and can significantly improve the merged network. |
| title | CoGraM: Context-sensitive granular optimization method with rollback for robust model fusion |
| topic | Machine Learning I.2.6; F.2.0 |
| url | https://arxiv.org/abs/2512.03610 |