FedCDC: A Collaborative Framework for Data Consumers in Federated Learning Market
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916631117037568 |
|---|---|
| author | Shi, Zhuan Ohl, Patrick Faltings, Boi |
| author_facet | Shi, Zhuan Ohl, Patrick Faltings, Boi |
| contents | Federated learning (FL) allows machine learning models to be trained on distributed datasets without directly accessing local data. In FL markets, numerous Data Consumers compete to recruit Data Owners for their respective training tasks, but budget constraints and competition can prevent them from securing sufficient data. While existing solutions focus on optimizing one-to-one matching between Data Owners and Data Consumers, we propose \methodname{}, a novel framework that facilitates collaborative recruitment and training for Data Consumers with similar tasks. Specifically, \methodname{} detects shared subtasks among multiple Data Consumers and coordinates the joint training of submodels specialized for these subtasks. Then, through ensemble distillation, these submodels are integrated into each Data Consumer global model. Experimental evaluations on three benchmark datasets demonstrate that restricting Data Consumers access to Data Owners significantly degrades model performance; however, by incorporating \methodname{}, this performance loss is effectively mitigated, resulting in substantial accuracy gains for all participating Data Consumers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19109 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedCDC: A Collaborative Framework for Data Consumers in Federated Learning Market Shi, Zhuan Ohl, Patrick Faltings, Boi Distributed, Parallel, and Cluster Computing Federated learning (FL) allows machine learning models to be trained on distributed datasets without directly accessing local data. In FL markets, numerous Data Consumers compete to recruit Data Owners for their respective training tasks, but budget constraints and competition can prevent them from securing sufficient data. While existing solutions focus on optimizing one-to-one matching between Data Owners and Data Consumers, we propose \methodname{}, a novel framework that facilitates collaborative recruitment and training for Data Consumers with similar tasks. Specifically, \methodname{} detects shared subtasks among multiple Data Consumers and coordinates the joint training of submodels specialized for these subtasks. Then, through ensemble distillation, these submodels are integrated into each Data Consumer global model. Experimental evaluations on three benchmark datasets demonstrate that restricting Data Consumers access to Data Owners significantly degrades model performance; however, by incorporating \methodname{}, this performance loss is effectively mitigated, resulting in substantial accuracy gains for all participating Data Consumers. |
| title | FedCDC: A Collaborative Framework for Data Consumers in Federated Learning Market |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2502.19109 |