EUVIMEDEUVIMED entdecken
Crossref

Block-RACS: Towards Reputation-Aware Client Selection and Monetization Mechanism for Federated Learning

Zahra Batool, Kaiwen Zhang, Matthew Toews

ACM SIGAPP Applied Computing Review · 2023-09 · 23 (3) · 49-65

DOI: 10.1145/3626307.3626311 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM SIGAPP Applied Computing Review, online erschienen am 29.09.2023. Verfasst von Zahra Batool und 2 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 59 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 integrating blockchain and smart contract technologies into FL can solve the two aforementioned issues. In this paper, we present Block-RACS (Blockchain-based Reputation Aware Client Selection), a mechanism for FL operating in a smart contract which rewards clients for their participation using cryptocurrencies. Block-RACS 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 Block-RACS to measure the relative contribution of each client by calculating a Shapley value and allocating rewards accordingly. Moreover, a blockchain-based reputation mechanism enables audibility and non-repudiation. The security analysis of the system is also presented to check the security vulnerabilities. We have implemented Block-RACS using Solidity and tested on the Ethereum blockchain with various popular datasets. Our results show that Block-RACS outperforms existing baseline schemes by improving accuracy and reducing the number of FL rounds.

Zitieren

APA

Batool, Z., Zhang, K., & Toews, M. (2023). Block-RACS: Towards Reputation-Aware Client Selection and Monetization Mechanism for Federated Learning. ACM SIGAPP Applied Computing Review, 23(3), 49-65. https://doi.org/10.1145/3626307.3626311

Vancouver

Batool Z, Zhang K, Toews M. Block-RACS: Towards Reputation-Aware Client Selection and Monetization Mechanism for Federated Learning. ACM SIGAPP Applied Computing Review. 2023;23(3):49-65. doi:10.1145/3626307.3626311

BibTeX
@article{Batool2023,
  author = {Batool, Zahra and Zhang, Kaiwen and Toews, Matthew},
  title = {Block-RACS: Towards Reputation-Aware Client Selection and Monetization Mechanism for Federated Learning},
  journal = {ACM SIGAPP Applied Computing Review},
  year = {2023},
  volume = {23},
  number = {3},
  pages = {49--65},
  doi = {10.1145/3626307.3626311}
}
Kostenlos starten →