1 citations · 1 across the 7 of their papers we have counts for
8 papers · 1 filter
Tram-FL: Reducing Communication and Computation Costs through Sequential Model Circulation in Decentralized Federated Learning
Kota Maejima, Takayuki Nishio, Asato Yamazaki +1
Conventional decentralized federated learning (DFL) often focuses on clients, with each client maintaining a model copy, performing updates individually, and undertaking model exch…
Enabling Federated Inference via Unsupervised Consensus Embedding
Yui Hashimoto, Takayuki Nishio, Yuichi Kitagawa +1
Cooperative inference across independently deployed machine learning models is increasingly desirable in distributed environments, as there is a growing need to leverage multiple m…
BlazeFL: Fast and Deterministic Federated Learning Simulation
Kitsuya Azuma, Takayuki Nishio
Federated learning (FL) research increasingly relies on single-node simulations with hundreds or thousands of virtual clients, making both efficiency and reproducibility essential.…
Multi-Station WiFi CSI Sensing Framework Robust to Station-wise Feature Missingness and Limited Labeled Data
Keita Kayano, Takayuki Nishio, Daiki Yoda +2
We propose a WiFi Channel State Information (CSI) sensing framework for multi-station deployments that addresses two fundamental challenges in practical CSI sensing: station-wise f…
Lightweight User-Personalization Method for Closed Split Computing
Yuya Okada, Takayuki Nishio
Split Computing enables collaborative inference between edge devices and the cloud by partitioning a deep neural network into an edge-side head and a server-side tail, reducing lat…
SALT: A Lightweight Model Adaptation Method for Closed Split Computing Environments
Yuya Okada, Takayuki Nishio
We propose SALT (Split-Adaptive Lightweight Tuning), a lightweight model adaptation framework for Split Computing under closed constraints, where the head and tail networks are pro…
Load-Aware Training Scheduling for Model Circulation-based Decentralized Federated Learning
Haruki Kainuma, Takayuki Nishio
This paper proposes Load-aware Tram-FL, an extension of Tram-FL that introduces a training scheduling mechanism to minimize total training time in decentralized federated learning…
Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation
Kitsuya Azuma, Takayuki Nishio, Yuichi Kitagawa +2
Federated Learning (FL) enables collaborative model training across decentralized clients, enhancing privacy by keeping data local. Yet conventional FL, relying on frequent paramet…