Improving Fairness for Data Valuation in Horizontal Federated Learning

Part of proceedings: ISBN 978-1-6654-0883-7QC 20221104
Federated learning is an emerging decentralized machine learning scheme that allows multiple data owners to work collaboratively while ensuring data privacy. The success of federated learning depends largely on the participation of data owners. To sustain and encourage data owners' participation, it is crucial to fairly evaluate the quality of the data provided by the data owners as well as their contribution to the final model and reward them correspondingly. Federated Shapley value, recently proposed by Wang et al. [Federated Learning, 2020], is a measure for data value under the framework of federated learning that satisfies many desired properties for data valuation. However, there are still factors of potential unfairness in the design of federated Shapley value because two data owners with the same local data may not receive the same evaluation. We propose a new measure called completed federated Shapley value to improve the fairness of federated Shapley value. The design depends on completing a matrix consisting of all the possible contributions by different subsets of the data owners. It is shown under mild conditions that this matrix is approximately low-rank by leveraging concepts and tools from optimization. Both theoretical analysis and empirical evaluation verify that the proposed measure does improve fairness in many circumstances.

Fang, HuangUniv British Columbia, Vancouver, BC, Canada. (författare)
Zhou, ZiruiHuawei Technol Canada Co, Markham, ON, Canada. (författare)
Pei, JianSimon Fraser Univ, Burnaby, BC, Canada. (författare)
Friedlander, Michael P.Univ British Columbia, Vancouver, BC, Canada. (författare)
Liu, ChangxinKTH,Reglerteknik(Swepub:kth)u1xs2gr3 (författare)
Zhang, YongHuawei Technol Canada Co, Markham, ON, Canada. (författare)
Univ British Columbia, Vancouver, BC, Canada.Huawei Technol Canada Co, Markham, ON, Canada. (creator_code:org_t)

Ingår i:38th IEEE International Conference on Data Engineering, ICDE 2022: Institute of Electrical and Electronics Engineers (IEEE), s. 2440-2453

Av författaren/redakt...: Fan, Zhenan; Fang, Huang; Zhou, Zirui; Pei, Jian; Friedlander, Mic ...; Liu, Changxin; visa fler...; Zhang, Yong; visa färre...

Om ämnet

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.