paper-with-me

홈 › Papers

Neural Tangent Kernel Empowered Federated Learning

2021-10-07 · Kai Yue, Richeng Jin, Ryan Pilgrim, Chau-Wai Wong, Dror Baron, Huaiyu Dai

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 are different from each other. Meanwhile, recent advances in the interpretation of neural networks have seen a wide use of neural tangent kernels (NTKs) for convergence analyses. In this paper, we propose a novel FL paradigm empowered by the NTK framework. The paradigm addresses the challenge of statistical heterogeneity by transmitting update data that are more expressive than those of the conventional FL paradigms. Specifically, sample-wise Jacobian matrices, rather than model weights/gradients, are uploaded by participants. The server then constructs an empirical kernel matrix to update a global model without explicitly performing gradient descent. We further develop a variant with improved communication efficiency and enhanced privacy. Numerical results show that the proposed paradigm can achieve the same accuracy while reducing the number of communication rounds by an order of magnitude compared to federated averaging.

📄 PDF Abstract BibTeX arXiv:2110.03681

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningPrivacy Preserving

Methods 이 논문이 사용한 방법론

NTK 설명 없음

Similar Papers 제목 키워드 기반

FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis

2021-05-11 · Baihe Huang, Xiaoxiao Li, Zhao Song, Xin Yang

Federated Learning (FL) is an emerging learning scheme that allows different distributed clients to train deep neural networks together without data sharing. Neural networks have become popular due to their unprecedented…

Federated Learning

TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels

2022-07-13 · Yaodong Yu, Alexander Wei, Sai Praneeth Karimireddy, Yi Ma 외

State-of-the-art federated learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. For neural networks, even when centralized SGD easily finds a solutio…

Federated Learning

Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning

2025-12-14 · Li Xia arxiv

Decentralized federated learning (DFL) enables collaborative model training without a central server, but converges slowly under statistical heterogeneity. Recent work has shown that neural tangent kernel (NTK) methods a…

Federated Learning

Reinforcement Learning via Gaussian Processes with Neural Network Dual Kernels

2020-04-10 · Imène R. Goumiri, Benjamin W. Priest, Michael D. Schneider

While deep neural networks (DNNs) and Gaussian Processes (GPs) are both popularly utilized to solve problems in reinforcement learning, both approaches feature undesirable drawbacks for challenging problems. DNNs learn c…

Gaussian Processesreinforcement-learningReinforcement LearningReinforcement Learning (RL)

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

2024-10-02 · Gabriel Thompson, Kai Yue, Chau-Wai Wong, Huaiyu Dai

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 heterog…

Federated Learning