The lottery ticket hypothesis (LTH) claims that a deep neural network (i.e., ground network) contains a number of subnetworks (i.e., winning tickets), each of which exhibiting identically accurate inference capability as that of the ground network. Federated learning (FL) has recently been applied in LotteryFL to discover such winning tickets in a distributed way, showing higher accuracy multi-task learning than Vanilla FL. Nonetheless, LotteryFL relies on unicast transmission on the downlink, and ignores mitigating stragglers, questioning scalability. Motivated by this, in this article we propose a personalized and communication-efficient federated lottery ticket learning algorithm, coined CELL, which exploits downlink broadcast for communication efficiency. Furthermore, it utilizes a novel user grouping method, thereby alternating between FL and lottery learning to mitigate stragglers. Numerical simulations validate that CELL achieves up to 3.6% higher personalized task classification accuracy with 4.3x smaller total communication cost until convergence under the CIFAR-10 dataset.
|Title of host publication||2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||5|
|Publication status||Published - 2021|
|Event||22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021 - Lucca, Italy|
Duration: 2021 Sep 27 → 2021 Sep 30
|Name||IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC|
|Conference||22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021|
|Period||21/9/27 → 21/9/30|
Bibliographical noteFunding Information:
This work was supported in part by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT), No.2018-0-00170, Korea-EU 5G joint project: Virtual Presence in Moving Objects through 5G (PriMO-5G, Online: https://primo-5g.eu), and in part by IITP grant funded by the Korea government (MSIT) No. 2021-0-00270, Development of 5G MEC framework to improve food factory productivity, automate and optimize flexible packaging.
© 2021 IEEE.
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering
- Computer Science Applications
- Information Systems