An incentive mechanism with bandwidth allocation for federated learning
Federated learning (FL) is an emerging machine learning paradigm that can make full use of crowd sourced mobile resources for training on decentralized data.However, it is challenging to deploy FL over a wireless network because of the limited bandwidth and clients’ selfishness.To address these chal...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
China InfoCom Media Group
2022-12-01
|
| Series: | 物联网学报 |
| Subjects: | |
| Online Access: | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2022.00300/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533697747058688 |
|---|---|
| author | Yingyun GUO Bo GAO Zhifei ZHANG Yu ZHANG Ke XIONG |
| author_facet | Yingyun GUO Bo GAO Zhifei ZHANG Yu ZHANG Ke XIONG |
| author_sort | Yingyun GUO |
| collection | DOAJ |
| description | Federated learning (FL) is an emerging machine learning paradigm that can make full use of crowd sourced mobile resources for training on decentralized data.However, it is challenging to deploy FL over a wireless network because of the limited bandwidth and clients’ selfishness.To address these challenges, an incentive mechanism with bandwidth allocation (IMBA) was proposed.Considering the difference between clients' data quality and computing power, IMBA designs a payment scheme to incentivize high-quality clients to contribute their computing resources, thus improving the training accuracy of the model.By minimizing the weight sum of training time and payment cost, the optimal payment and bandwidth allocation scheme was determined, and the training delay was reduced by optimizing bandwidth allocation.Experiments show that IMBA effectively improves training accuracy, reduces the training delay and helps the server flexibly balance training delay and hiring payment. |
| format | Article |
| id | doaj-art-1ecd5a7197684b24890140800eaba1fe |
| institution | Kabale University |
| issn | 2096-3750 |
| language | zho |
| publishDate | 2022-12-01 |
| publisher | China InfoCom Media Group |
| record_format | Article |
| series | 物联网学报 |
| spelling | doaj-art-1ecd5a7197684b24890140800eaba1fe2025-01-15T02:54:46ZzhoChina InfoCom Media Group物联网学报2096-37502022-12-016829259580525An incentive mechanism with bandwidth allocation for federated learningYingyun GUOBo GAOZhifei ZHANGYu ZHANGKe XIONGFederated learning (FL) is an emerging machine learning paradigm that can make full use of crowd sourced mobile resources for training on decentralized data.However, it is challenging to deploy FL over a wireless network because of the limited bandwidth and clients’ selfishness.To address these challenges, an incentive mechanism with bandwidth allocation (IMBA) was proposed.Considering the difference between clients' data quality and computing power, IMBA designs a payment scheme to incentivize high-quality clients to contribute their computing resources, thus improving the training accuracy of the model.By minimizing the weight sum of training time and payment cost, the optimal payment and bandwidth allocation scheme was determined, and the training delay was reduced by optimizing bandwidth allocation.Experiments show that IMBA effectively improves training accuracy, reduces the training delay and helps the server flexibly balance training delay and hiring payment.http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2022.00300/federated learningincentive mechanismbandwidth allocationStackelberg gametraining quality |
| spellingShingle | Yingyun GUO Bo GAO Zhifei ZHANG Yu ZHANG Ke XIONG An incentive mechanism with bandwidth allocation for federated learning 物联网学报 federated learning incentive mechanism bandwidth allocation Stackelberg game training quality |
| title | An incentive mechanism with bandwidth allocation for federated learning |
| title_full | An incentive mechanism with bandwidth allocation for federated learning |
| title_fullStr | An incentive mechanism with bandwidth allocation for federated learning |
| title_full_unstemmed | An incentive mechanism with bandwidth allocation for federated learning |
| title_short | An incentive mechanism with bandwidth allocation for federated learning |
| title_sort | incentive mechanism with bandwidth allocation for federated learning |
| topic | federated learning incentive mechanism bandwidth allocation Stackelberg game training quality |
| url | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2022.00300/ |
| work_keys_str_mv | AT yingyunguo anincentivemechanismwithbandwidthallocationforfederatedlearning AT bogao anincentivemechanismwithbandwidthallocationforfederatedlearning AT zhifeizhang anincentivemechanismwithbandwidthallocationforfederatedlearning AT yuzhang anincentivemechanismwithbandwidthallocationforfederatedlearning AT kexiong anincentivemechanismwithbandwidthallocationforfederatedlearning AT yingyunguo incentivemechanismwithbandwidthallocationforfederatedlearning AT bogao incentivemechanismwithbandwidthallocationforfederatedlearning AT zhifeizhang incentivemechanismwithbandwidthallocationforfederatedlearning AT yuzhang incentivemechanismwithbandwidthallocationforfederatedlearning AT kexiong incentivemechanismwithbandwidthallocationforfederatedlearning |