AI Chat AI Image Generator AI Video Text to Speech

A Secure Aggregation for Federated Learning on Long-Tailed Data

07/17/2023

∙

by Yanna Jiang, et al.

∙

∙

As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with the presence of Byzantine nodes in the FL scenario. A novel two-layer aggregation method is proposed for the rejection of malicious models and the advisable selection of valuable models containing tail class data information. We introduce the concept of think tank to leverage the wisdom of all participants. Preliminary experiments validate that the think tank can make effective model selections for global aggregation.

Yanna Jiang
3 publications
Baihe Ma
3 publications
Xu Wang
80 publications
Guangsheng Yu
10 publications
Caijun Sun
3 publications
Wei Ni
37 publications
Ren Ping Liu
12 publications

page 1

page 2

page 3

page 4

research

∙ 04/28/2022

Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features

Federated learning (FL) provides a privacy-preserving solution for distr...

0 Xinyi Shang, et al. ∙

research

∙ 12/29/2021

Federated Learning for Cross-block Oil-water Layer Identification

Cross-block oil-water layer(OWL) identification is essential for petrole...

0 Bingyang Chena, et al. ∙

research

∙ 06/30/2022

Towards Federated Long-Tailed Learning

Data privacy and class imbalance are the norm rather than the exception ...

0 Zihan Chen, et al. ∙

research

∙ 10/04/2022

Shielding Federated Learning: Mitigating Byzantine Attacks with Less Constraints

Federated learning is a newly emerging distributed learning framework th...

0 Minghui Li, et al. ∙

research

∙ 10/29/2022

Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance

While being an effective framework of learning a shared model across mul...

0 Youngjoon Lee, et al. ∙

research

∙ 08/21/2023

Federated Learning Robust to Byzantine Attacks: Achieving Zero Optimality Gap

In this paper, we propose a robust aggregation method for federated lear...

0 Shiyuan Zuo, et al. ∙

research

∙ 04/30/2022

FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation

Federated learning provides a privacy guarantee for generating good deep...

14 Xinyi Shang, et al. ∙