On the effects of similarity metrics in decentralized deep learning under distributional shift
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916622260764672 |
|---|---|
| author | Zec, Edvin Listo Hagander, Tom Ihre-Thomason, Eric Girdzijauskas, Sarunas |
| author_facet | Zec, Edvin Listo Hagander, Tom Ihre-Thomason, Eric Girdzijauskas, Sarunas |
| contents | Decentralized Learning (DL) enables privacy-preserving collaboration among organizations or users to enhance the performance of local deep learning models. However, model aggregation becomes challenging when client data is heterogeneous, and identifying compatible collaborators without direct data exchange remains a pressing issue. In this paper, we investigate the effectiveness of various similarity metrics in DL for identifying peers for model merging, conducting an empirical analysis across multiple datasets with distribution shifts. Our research provides insights into the performance of these metrics, examining their role in facilitating effective collaboration. By exploring the strengths and limitations of these metrics, we contribute to the development of robust DL methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10720 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the effects of similarity metrics in decentralized deep learning under distributional shift Zec, Edvin Listo Hagander, Tom Ihre-Thomason, Eric Girdzijauskas, Sarunas Machine Learning Decentralized Learning (DL) enables privacy-preserving collaboration among organizations or users to enhance the performance of local deep learning models. However, model aggregation becomes challenging when client data is heterogeneous, and identifying compatible collaborators without direct data exchange remains a pressing issue. In this paper, we investigate the effectiveness of various similarity metrics in DL for identifying peers for model merging, conducting an empirical analysis across multiple datasets with distribution shifts. Our research provides insights into the performance of these metrics, examining their role in facilitating effective collaboration. By exploring the strengths and limitations of these metrics, we contribute to the development of robust DL methods. |
| title | On the effects of similarity metrics in decentralized deep learning under distributional shift |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2409.10720 |