output
20182023
most citedClient Selection for Federated Learning with Heterogeneous Resources in Mobile Edge

1.6k citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions

7 papers

cs.MA2023

Periodic Multi-Agent Path Planning

Kazumi Kasaura, Ryo Yonetani, Mai Nishimura

Multi-agent path planning (MAPP) is the problem of planning collision-free trajectories from start to goal locations for a team of agents. This work explores a relatively unexplore…

cond-mat.mtrl-sci2022★ 3 cited

Neural Structure Fields with Application to Crystal Structure Autoencoders

Naoya Chiba, Yuta Suzuki, Tatsunori Taniai +4

Representing crystal structures of materials to facilitate determining them via neural networks is crucial for enabling machine-learning applications involving crystal structure es…

cs.CV2021★ 9 cited

Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation

Takehiko Ohkawa, Takuma Yagi, Atsushi Hashimoto +2

Hand segmentation is a crucial task in first-person vision. Since first-person images exhibit strong bias in appearance among different environments, adapting a pre-trained segment…

cs.LG2020★ 22 cited

Path Planning using Neural A* Search

Ryo Yonetani, Tatsunori Taniai, Mohammadamin Barekatain +2

We present Neural A*, a novel data-driven search method for path planning problems. Despite the recent increasing attention to data-driven path planning, machine learning approache…

cs.LG2019★ 10 cited

MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics

Mohammadamin Barekatain, Ryo Yonetani, Masashi Hamaya

Transfer reinforcement learning (RL) aims at improving the learning efficiency of an agent by exploiting knowledge from other source agents trained on relevant tasks. However, it r…

cs.LG2019★ 17 cited

Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data

Naoya Yoshida, Takayuki Nishio, Masahiro Morikura +2

This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine le…

cs.NI2018★ 1.6k cited

Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge

Takayuki Nishio, Ryo Yonetani

We envision a mobile edge computing (MEC) framework for machine learning (ML) technologies, which leverages distributed client data and computation resources for training high-perf…