paper-with-me

Papers

Federated Knowledge Distillation

2020-11-04 · Hyowoon Seo, Jihong Park, Seungeun Oh, Mehdi Bennis, Seong-Lyun Kim

Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under limited communication resources, however, such a method becomes extremely costly particularly for modern deep neural networks having a huge number of model parameters. In this regard, federated distillation (FD) is a compelling distributed learning solution that only exchanges the model outputs whose dimensions are commonly much smaller than the model sizes (e.g., 10 labels in the MNIST dataset). The goal of this chapter is to provide a deep understanding of FD while demonstrating its communication efficiency and applicability to a variety of tasks. To this end, towards demystifying the operational principle of FD, the first part of this chapter provides a novel asymptotic analysis for two foundational algorithms of FD, namely knowledge distillation (KD) and co-distillation (CD), by exploiting the theory of neural tangent kernel (NTK). Next, the second part elaborates on a baseline implementation of FD for a classification task, and illustrates its performance in terms of accuracy and communication efficiency compared to FL. Lastly, to demonstrate the applicability of FD to various distributed learning tasks and environments, the third part presents two selected applications, namely FD over asymmetric uplink-and-downlink wireless channels and FD for reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2011.02367

Code (4)

TsingZ0/GFL pytorch
TsingZ0/PFL-Non-IID pytorch
eternal-f1ame/DaFKD2023 pytorch
zhuangdizhu/FedGen pytorch

Tasks

Federated LearningKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks

2022-01-10 · Lingzhi Gao, Zhenyuan Zhang, Chao Wu

While existing federated learning approaches primarily focus on aggregating local models to construct a global model, in realistic settings, some clients may be reluctant to share their private models due to the inclusio…

Data-free Knowledge DistillationFederated LearningGenerative Adversarial NetworkKnowledge Distillation

Improving Communication Efficiency of Federated Distillation via Accumulating Local Updates

2023-12-07 · Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu 외

As an emerging federated learning paradigm, federated distillation enables communication-efficient model training by transmitting only small-scale knowledge during the learning process. To further improve the communicati…

Federated Learning

Heterogeneous Federated Learning Using Knowledge Codistillation

2023-10-04 · Jared Lichtarge, Ehsan Amid, Shankar Kumar, Tien-Ju Yang 외

Federated Averaging, and many federated learning algorithm variants which build upon it, have a limitation: all clients must share the same model architecture. This results in unused modeling capacity on many clients, wh…

Federated Learningimage-classificationImage ClassificationKnowledge Distillation+2

Tailored Federated Learning: Leveraging Direction Regulation & Knowledge Distillation

2024-09-29 · Huidong Tang, Chen Li, Huachong Yu, Sayaka Kamei 외

Federated learning (FL) has emerged as a transformative training paradigm, particularly invaluable in privacy-sensitive domains like healthcare. However, client heterogeneity in data, computing power, and tasks poses a s…

Federated LearningKnowledge Distillation

Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning

2025-07-14 · Yichen Li

Model-Heterogeneous Federated Learning (Hetero-FL) has attracted growing attention for its ability to aggregate knowledge from heterogeneous models while keeping private data locally. To better aggregate knowledge from c…

Federated LearningKnowledge Distillation