TY - GEN
T1 - FL-MAB
T2 - 37th ACM/SIGAPP Symposium on Applied Computing, SAC 2022
AU - Batool, Zahra
AU - Zhang, Kaiwen
AU - Toews, Matthew
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/4/25
Y1 - 2022/4/25
N2 - Federated Learning (FL) is a promising solution for training using data collected from heterogeneous sources (e.g., mobile devices) while avoiding the transmission of large amounts of raw data and preserving privacy. Current FL approaches operate in an iterative manner by selecting a subset of participants each round, asking them to training using their latest local data over the most recent version of the global model, before collecting these local model updates and aggregating them to form the next iteration of the global model, and so forth until convergence is reached. Unfortunately, existing FL approaches typically select randomly the set of clients to use each round, which can negatively impact the quality of the model trained, as well the training round time due to the straggler problem. Moreover, clients, especially mobile devices with limited resources, should be incentivized to participate as federated learning is essentially a form of crowdsourcing for AI which requires monetization. We argue that the integration of blockchain and smart contract technologies to FL can solve the two aforementioned issues. In this paper, we present FL-MAB (FL- Multi-Auction using Blockchain), a client selection mechanism for FL operating in a smart contract which rewards clients for their participation using cryptocurrencies. FL-MAB employs a multidimensional auction mechanism for selecting users based on the compute and network resources offered by each client, as well as the quality of their local data. This auction is realized in a reliable and auditable manner through a smart contract. This allows FL-MAB to measure the relative contribution of each client by calculating a Shapley value, and allocating rewards accordingly. We have implemented FL-MAB using Solidity and tested on the Ethereum blockchain with various popular datasets. Our results show that FL-MAB outperforms existing baseline schemes by improving accuracy and reducing the no. of FL rounds.
AB - Federated Learning (FL) is a promising solution for training using data collected from heterogeneous sources (e.g., mobile devices) while avoiding the transmission of large amounts of raw data and preserving privacy. Current FL approaches operate in an iterative manner by selecting a subset of participants each round, asking them to training using their latest local data over the most recent version of the global model, before collecting these local model updates and aggregating them to form the next iteration of the global model, and so forth until convergence is reached. Unfortunately, existing FL approaches typically select randomly the set of clients to use each round, which can negatively impact the quality of the model trained, as well the training round time due to the straggler problem. Moreover, clients, especially mobile devices with limited resources, should be incentivized to participate as federated learning is essentially a form of crowdsourcing for AI which requires monetization. We argue that the integration of blockchain and smart contract technologies to FL can solve the two aforementioned issues. In this paper, we present FL-MAB (FL- Multi-Auction using Blockchain), a client selection mechanism for FL operating in a smart contract which rewards clients for their participation using cryptocurrencies. FL-MAB employs a multidimensional auction mechanism for selecting users based on the compute and network resources offered by each client, as well as the quality of their local data. This auction is realized in a reliable and auditable manner through a smart contract. This allows FL-MAB to measure the relative contribution of each client by calculating a Shapley value, and allocating rewards accordingly. We have implemented FL-MAB using Solidity and tested on the Ethereum blockchain with various popular datasets. Our results show that FL-MAB outperforms existing baseline schemes by improving accuracy and reducing the no. of FL rounds.
KW - auction
KW - blockchain
KW - client selection
KW - federated learning
KW - monetization
KW - smart contracts
UR - https://www.scopus.com/pages/publications/85130391584
U2 - 10.1145/3477314.3507050
DO - 10.1145/3477314.3507050
M3 - Contribution to conference proceedings
AN - SCOPUS:85130391584
T3 - Proceedings of the ACM Symposium on Applied Computing
SP - 299
EP - 307
BT - Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing, SAC 2022
PB - Association for Computing Machinery
Y2 - 25 April 2022 through 29 April 2022
ER -