no code implementations • 1 Apr 2021 • Akihito Taya, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto
Because FL algorithms hardly converge the parameters of machine learning (ML) models, this paper focuses on the convergence of ML models in function spaces.
no code implementations • 16 Feb 2021 • Masao Shinzaki, Yusuke Koda, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura, Yushi Shirato, Daisei Uchida, Naoki Kita
Second, we demonstrate the feasibility of \textit{zero-shot adaptation} as a solution, where a learning agent adapts to environmental parameters unseen during training.
no code implementations • 29 Sep 2020 • Naoya Yoshida, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto
This paper proposes a multi-armed bandit (MAB)-based client selection method to solve the exploration and exploitation trade-off and reduce the time consumption for FL in mobile networks.
Networking and Internet Architecture
no code implementations • 14 Aug 2020 • Sohei Itahara, Takayuki Nishio, Yusuke Koda, Masahiro Morikura, Koji Yamamoto
To this end, based on the idea of leveraging an unlabeled open dataset, we propose a distillation-based semi-supervised FL (DS-FL) algorithm that exchanges the outputs of local models among mobile devices, instead of model parameter exchange employed by the typical frameworks.
no code implementations • 21 Apr 2020 • Sohei Itahara, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto
The key idea of the proposed method is to obtain a ``good'' subnetwork from the original NN using the unlabeled data based on the lottery hypothesis.
no code implementations • 14 Apr 2020 • Yusuke Koda, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura
To this end, a differentially private AirComp-based FL is designed in this study, where the key idea is to harness receiver noise perturbation injected to aggregated global models inherently, thereby preventing the inference of clients' private data.
Networking and Internet Architecture Signal Processing
no code implementations • 17 May 2019 • Naoya Yoshida, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto, Ryo Yonetani
Therefore, to mitigate the degradation induced by non-IID data, we assume that a limited number (e. g., less than 1%) of clients allow their data to be uploaded to a server, and we propose a hybrid learning mechanism referred to as Hybrid-FL, wherein the server updates the model using the data gathered from the clients and aggregates the model with the models trained by clients.
no code implementations • 17 May 2019 • Kota Nakashima, Shotaro Kamiya, Kazuki Ohtsu, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura
In densely deployed WLANs, the number of the available topologies of APs is extremely high, and thus we extract the features of the topological structures based on GCNs.