<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>federated learning on Chiara Camerota</title><link>https://camerotachiara.github.io/tags/federated-learning/</link><description>Recent content in federated learning on Chiara Camerota</description><generator>Hugo -- 0.114.0</generator><language>en</language><atom:link href="https://camerotachiara.github.io/tags/federated-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>Taming Bandwidth Bottlenecks in Federated Learning via ECN-based Gradient Compression</title><link>https://camerotachiara.github.io/papers/paper_cnsm/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://camerotachiara.github.io/papers/paper_cnsm/</guid><description>The paper addresses communication bottlenecks in Federated Learning and introduces Selective Compression via Adaptive Lightweight Protocol, which dynamically selects compression levels based on local gradient variance and uplink bandwidth. Published on 2025 21st International Conference on Network and Service Management (CNSM).</description></item></channel></rss>