Optimizing Split Points for Error-Resilient SplitFed Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929365737013248 |
|---|---|
| author | Shiranthika, Chamani Saeedi, Parvaneh Bajić, Ivan V. |
| author_facet | Shiranthika, Chamani Saeedi, Parvaneh Bajić, Ivan V. |
| contents | Recent advancements in decentralized learning, such as Federated Learning (FL), Split Learning (SL), and Split Federated Learning (SplitFed), have expanded the potentials of machine learning. SplitFed aims to minimize the computational burden on individual clients in FL and parallelize SL while maintaining privacy. This study investigates the resilience of SplitFed to packet loss at model split points. It explores various parameter aggregation strategies of SplitFed by examining the impact of splitting the model at different points-either shallow split or deep split-on the final global model performance. The experiments, conducted on a human embryo image segmentation task, reveal a statistically significant advantage of a deeper split point. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19453 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimizing Split Points for Error-Resilient SplitFed Learning Shiranthika, Chamani Saeedi, Parvaneh Bajić, Ivan V. Artificial Intelligence Recent advancements in decentralized learning, such as Federated Learning (FL), Split Learning (SL), and Split Federated Learning (SplitFed), have expanded the potentials of machine learning. SplitFed aims to minimize the computational burden on individual clients in FL and parallelize SL while maintaining privacy. This study investigates the resilience of SplitFed to packet loss at model split points. It explores various parameter aggregation strategies of SplitFed by examining the impact of splitting the model at different points-either shallow split or deep split-on the final global model performance. The experiments, conducted on a human embryo image segmentation task, reveal a statistically significant advantage of a deeper split point. |
| title | Optimizing Split Points for Error-Resilient SplitFed Learning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2405.19453 |