DC Field | Value | Language |
---|---|---|
dc.contributor.author | HAN, DONGJUN | ko |
dc.contributor.author | Moon, Jaekyun | ko |
dc.contributor.author | Bhatti, Hasnain Irshad | ko |
dc.contributor.author | Lee, Jungmoon | ko |
dc.date.accessioned | 2021-11-25T06:43:32Z | - |
dc.date.available | 2021-11-25T06:43:32Z | - |
dc.date.created | 2021-11-25 | - |
dc.date.issued | 2021-07-24 | - |
dc.identifier.citation | ICML 2021 Workshop on Federated Learning for User Privacy and Data Confidentiality | - |
dc.identifier.uri | http://hdl.handle.net/10203/289476 | - |
dc.description.abstract | Federated learning (FL) operates based on model exchanges between the server and the clients, and suffers from significant communication as well as client-side computation burden. While emerging split learning (SL) solutions can reduce the clientside computation burden by splitting the model architecture, SL-based ideas still require significant time delay and communication burden for transmitting the forward activations and backward gradients at every global round. In this paper, we propose a new direction to FL/SL based on updating the client/server-side models in parallel, via local-loss-based training specifically geared to split learning. The parallel training of split models substantially shortens latency while obviating server-to-clients communication. We provide latency analysis that leads to optimal model cut as well as general guidelines for splitting the model. We also provide a theoretical analysis for guaranteeing convergence of our method. Extensive experimental results indicate that our scheme has significant communication and latency advantages over existing FL and SL ideas. | - |
dc.language | English | - |
dc.publisher | ICML Board | - |
dc.title | Accelerating Federated Learning with Split Learning on Locally Generated Losses | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | ICML 2021 Workshop on Federated Learning for User Privacy and Data Confidentiality | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.contributor.localauthor | Moon, Jaekyun | - |
dc.contributor.nonIdAuthor | Bhatti, Hasnain Irshad | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.