Kai Yue — accepted AI-conference papers

2025

NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel

Gabriel Thompson, Kai Yue, Chau-Wai Wong, Huaiyu Dai

ICML 2025poster

Decentralized federated learning (DFL) is a collaborative machine learning framework for training a model across participants without a central server or raw data exchange. DFL faces challenges due to statistical heterogeneity, as participants often possess data of different distributions reflecting…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Neural Tangent Kernel Empowered Federated Learning

Kai Yue, Richeng Jin, Ryan Pilgrim, Chau-Wai Wong, Dror Baron, Huaiyu Dai

ICML 2022spotlight

Federated learning (FL) is a privacy-preserving paradigm where multiple participants jointly solve a machine learning problem without sharing raw data. Unlike traditional distributed learning, a unique characteristic of FL is statistical heterogeneity, namely, data distributions across participants…

Cited by 23 Source ↗PDF ↗code ↗Scholar ↗