FedRAD: Federated Robust Adaptive Distillation

by   Stefán Páll Sturluson, et al.

The robustness of federated learning (FL) is vital for the distributed training of an accurate global model that is shared among large number of clients. The collaborative learning framework by typically aggregating model updates is vulnerable to model poisoning attacks from adversarial clients. Since the shared information between the global server and participants are only limited to model parameters, it is challenging to detect bad model updates. Moreover, real-world datasets are usually heterogeneous and not independent and identically distributed (Non-IID) among participants, which makes the design of such robust FL pipeline more difficult. In this work, we propose a novel robust aggregation method, Federated Robust Adaptive Distillation (FedRAD), to detect adversaries and robustly aggregate local models based on properties of the median statistic, and then performing an adapted version of ensemble Knowledge Distillation. We run extensive experiments to evaluate the proposed method against recently published works. The results show that FedRAD outperforms all other aggregators in the presence of adversaries, as well as in heterogeneous data distributions.



page 1

page 2

page 3

page 4


Global Knowledge Distillation in Federated Learning

Knowledge distillation has caught a lot of attention in Federated Learni...

No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices

Federated learning (FL) is an important paradigm for training global mod...

Towards Building a Robust and Fair Federated Learning System

Federated Learning (FL) has emerged as a promising practical framework f...

Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning

Federated learning (FL) enables edge-devices to collaboratively learn a ...

RC-SSFL: Towards Robust and Communication-efficient Semi-supervised Federated Learning System

Federated Learning (FL) is an emerging decentralized artificial intellig...

CD^2-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning

Federated learning (FL) is a distributed learning paradigm that enables ...

Federated Adversarial Training with Transformers

Federated learning (FL) has emerged to enable global model training over...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.