Saved in:
Bibliographic Details
Main Authors: Xu, Kaidi, Zhou, Shenglong, Li, Geoffrey Ye
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.19476
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911020420694016
author Xu, Kaidi
Zhou, Shenglong
Li, Geoffrey Ye
author_facet Xu, Kaidi
Zhou, Shenglong
Li, Geoffrey Ye
contents Future wireless networks are expected to be AI-empowered, making their performance highly dependent on the quality of training datasets. However, physical-layer entities often observe only partial wireless environments characterized by different power delay profiles. Federated learning is capable of addressing this limited observability, but often struggles with data heterogeneity. To tackle this challenge, we propose a neural collapse (NC) inspired deep supervised federated learning (NCDSFL) algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19476
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Collapse based Deep Supervised Federated Learning for Signal Detection in OFDM Systems
Xu, Kaidi
Zhou, Shenglong
Li, Geoffrey Ye
Signal Processing
Future wireless networks are expected to be AI-empowered, making their performance highly dependent on the quality of training datasets. However, physical-layer entities often observe only partial wireless environments characterized by different power delay profiles. Federated learning is capable of addressing this limited observability, but often struggles with data heterogeneity. To tackle this challenge, we propose a neural collapse (NC) inspired deep supervised federated learning (NCDSFL) algorithm.
title Neural Collapse based Deep Supervised Federated Learning for Signal Detection in OFDM Systems
topic Signal Processing
url https://arxiv.org/abs/2506.19476