Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SplitFed: When Federated Learning Meets Split Learning

About

Federated learning (FL) and split learning (SL) are two popular distributed machine learning approaches. Both follow a model-to-data scenario; clients train and test machine learning models without sharing raw data. SL provides better model privacy than FL due to the machine learning model architecture split between clients and the server. Moreover, the split model makes SL a better option for resource-constrained environments. However, SL performs slower than FL due to the relay-based training across multiple clients. In this regard, this paper presents a novel approach, named splitfed learning (SFL), that amalgamates the two approaches eliminating their inherent drawbacks, along with a refined architectural configuration incorporating differential privacy and PixelDP to enhance data privacy and model robustness. Our analysis and empirical results demonstrate that (pure) SFL provides similar test accuracy and communication efficiency as SL while significantly decreasing its computation time per global epoch than in SL for multiple clients. Furthermore, as in SL, its communication efficiency over FL improves with the number of clients. Besides, the performance of SFL with privacy and robustness measures is further evaluated under extended experimental settings.

Chandra Thapa, M.A.P. Chamikara, Seyit Camtepe, Lichao Sun• 2020

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-100 (test)
Top-1 Acc65.92
287
Image ClassificationCIFAR-10 IID
Accuracy77.5
166
Image ClassificationCIFAR10 non-iid
Accuracy69.3
162
Image ClassificationCIFAR-100 non-IID (test)
Test Accuracy (Avg Best)39.5
113
Image ClassificationCIFAR-100 IID
Accuracy43.2
42
Semantic segmentationEmbryo image dataset (test)
Accuracy (%)93.39
21
Image ClassificationCIFAR-10 (test)
Accuracy91.07
19
Image ClassificationCIFAR-10 (test)
Test Accuracy86.2
10
Image ClassificationCIFAR-100 (test)
Test Accuracy71.5
10
Showing 9 of 9 rows

Other info

Follow for update