Contrastive Federated Learning with Tabular Data Silos
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915151425306624 |
|---|---|
| author | Ginanjar, Achmad Li, Xue Hua, Wen Pei, Jiaming |
| author_facet | Ginanjar, Achmad Li, Xue Hua, Wen Pei, Jiaming |
| contents | Learning from vertical partitioned data silos is challenging due to the segmented nature of data, sample misalignment, and strict privacy concerns. Federated learning has been proposed as a solution. However, sample misalignment across silos often hinders optimal model performance and suggests data sharing within the model, which breaks privacy. Our proposed solution is Contrastive Federated Learning with Tabular Data Silos (CFL), which offers a solution for data silos with sample misalignment without the need for sharing original or representative data to maintain privacy. CFL begins with local acquisition of contrastive representations of the data within each silo and aggregates knowledge from other silos through the federated learning algorithm. Our experiments demonstrate that CFL solves the limitations of existing algorithms for data silos and outperforms existing tabular contrastive learning. CFL provides performance improvements without loosening privacy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_06123 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Contrastive Federated Learning with Tabular Data Silos Ginanjar, Achmad Li, Xue Hua, Wen Pei, Jiaming Machine Learning 68A00 I.1.1 Learning from vertical partitioned data silos is challenging due to the segmented nature of data, sample misalignment, and strict privacy concerns. Federated learning has been proposed as a solution. However, sample misalignment across silos often hinders optimal model performance and suggests data sharing within the model, which breaks privacy. Our proposed solution is Contrastive Federated Learning with Tabular Data Silos (CFL), which offers a solution for data silos with sample misalignment without the need for sharing original or representative data to maintain privacy. CFL begins with local acquisition of contrastive representations of the data within each silo and aggregates knowledge from other silos through the federated learning algorithm. Our experiments demonstrate that CFL solves the limitations of existing algorithms for data silos and outperforms existing tabular contrastive learning. CFL provides performance improvements without loosening privacy. |
| title | Contrastive Federated Learning with Tabular Data Silos |
| topic | Machine Learning 68A00 I.1.1 |
| url | https://arxiv.org/abs/2409.06123 |