Federated Learning  enables distributed devices to learn a shared machine learning model together, without uploading their private training data. It has received significant attention recently and has been used in mobile applications such as search suggestion  and object detection . Federated Learning is different from distributed machine learning due to the following reasons: 1) System heterogeneity: federated learning is usually performed on devices having highly dynamic and heterogeneous network, compute, and power availability. 2) Data heterogeneity (or statistical heterogeneity): data is produced by different users on different devices, and therefore may have different statistical distribution (non-IID).
|Original language||English (US)|
|Title of host publication||Proceedings - 2020 IEEE/ACM Symposium on Edge Computing, SEC 2020|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||3|
|State||Published - Nov 2020|
|Event||5th IEEE/ACM Symposium on Edge Computing, SEC 2020 - Virtual, San Jose, United States|
Duration: Nov 11 2020 → Nov 13 2020
|Name||Proceedings - 2020 IEEE/ACM Symposium on Edge Computing, SEC 2020|
|Conference||5th IEEE/ACM Symposium on Edge Computing, SEC 2020|
|City||Virtual, San Jose|
|Period||11/11/20 → 11/13/20|
Bibliographical noteFunding Information:
∗This research was supported in part by NSF under grant CNS-1717834.
© 2020 IEEE.
Copyright 2021 Elsevier B.V., All rights reserved.