Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning

Wenke Huang, Mang Ye, Zekun Shi, Guancheng Wan, He Li +1 more
2/3/2026

No official code found. Best implementation: WenkeHuang/FDCR (11 stars, last commit 2025-06-21).

Abstract

.

DOISemantic Scholar

Code Implementations(1)

WenkeHuang/FDCRCommunity72%

NeruIPS2024 - Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated LearningAdd commentMore actions

111PythonSep 26, 20241 years ago

Similar Papers

Context Consistency Regularization for Label Sparsity in Time Series

99% match1 repo222026

Regularized Parameter Uncertainty for Improving Generalization in Reinforcement Learning

99% match2026

Scaling Laws for Downstream Task Performance in Machine Translation

98% match2026

A Benchmark for Semantic Sensitive Information in LLMs Outputs

98% match2026

Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification

98% match2026

Unsupervised Domain Adaptation for Anatomical Structure Detection in Ultrasound Images

98% match1 repo112026

Cite this paper

@article{huang2026parameter,
  title  = {Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning},
  author = {Wenke Huang and Mang Ye and Zekun Shi and Guancheng Wan and He Li and Bo Du},
  year   = {2026},
  doi    = {10.52202/079017-3843},
  url    = {https://doi.org/10.52202/079017-3843},
  journal = {NEURIPS 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/668a39a607650855f54f923790fb2bdbdcd74722.svg)](https://codeofpaper.com/paper/668a39a607650855f54f923790fb2bdbdcd74722)

Discussion