1 code implementation • 1 May 2023 • Konstantin D. Pandl, Chun-Yin Huang, Ivan Beschastnikh, Xiaoxiao Li, Scott Thiebes, Ali Sunyaev
The valuation of data points through DDVal allows to also draw hierarchical conclusions on the contribution of institutions, and we empirically show that the accuracy of DDVal in estimating institutional contributions is higher than existing Shapley value approximation methods for federated learning.
no code implementations • 3 Dec 2022 • Shiqi He, Qifan Yan, Feijie Wu, Lanjun Wang, Mathias Lécuyer, Ivan Beschastnikh
Federated learning (FL) is an effective technique to directly involve edge devices in machine learning training while preserving client privacy.
1 code implementation • 6 Oct 2021 • Yan Xiao, Yun Lin, Ivan Beschastnikh, Changsheng Sun, David S. Rosenblum, Jin Song Dong
However, inputs may deviate from the training dataset distribution in real deployments.
no code implementations • 22 Nov 2020 • Jiang Zhang, Ivan Beschastnikh, Sergey Mechtaev, Abhik Roychoudhury
Data-driven decision making is gaining prominence with the popularity of various machine learning models.
1 code implementation • 24 Dec 2018 • Fabian Ruffy, Michael Przystupa, Ivan Beschastnikh
We present a new emulator, Iroko, which we developed to support different network topologies, congestion control algorithms, and deployment scenarios.
2 code implementations • 24 Nov 2018 • Muhammad Shayan, Clement Fung, Chris J. M. Yoon, Ivan Beschastnikh
Federated Learning is the current state of the art in supporting secure multi-party machine learning (ML): data is maintained on the owner's device and the updates to the model are aggregated through a secure protocol.
1 code implementation • 23 Nov 2018 • Clement Fung, Jamie Koerner, Stewart Grant, Ivan Beschastnikh
Distributed machine learning (ML) systems today use an unsophisticated threat model: data sources must trust a central ML process.
2 code implementations • 14 Aug 2018 • Clement Fung, Chris J. M. Yoon, Ivan Beschastnikh
Unfortunately, such approaches are susceptible to a variety of attacks, including model poisoning, which is made substantially worse in the presence of sybils.