<?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 Tenu Tech Brief</title>
    <link>https://cluster-site.onrender.com/tags/federated-learning/</link>
    <description>Recent content in Federated-Learning on Tenu Tech Brief</description>
    <generator>Hugo -- 0.146.0</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 24 Feb 2026 06:06:03 +0000</lastBuildDate>
    <atom:link href="https://cluster-site.onrender.com/tags/federated-learning/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>A Hierarchical Gradient Tracking Algorithm for Mitigating Subnet-Drift in Fog Learning Networks</title>
      <link>https://cluster-site.onrender.com/posts/a-hierarchical-gradient-tracking-algorithm-for-mitigating-subnet-drift-in-fog-learning-networks/</link>
      <pubDate>Tue, 24 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/a-hierarchical-gradient-tracking-algorithm-for-mitigating-subnet-drift-in-fog-learning-networks/</guid>
      <description>• Introduces SD‑GT, a semi‑decentralized gradient‑tracking method for fog‑based federated learning. • Eliminates gradient‑diversity assumptions, enabling robust training across hig</description>
    </item>
    <item>
      <title>EMS-FL: Federated Tuning of Mixture-of-Experts in Satellite-Terrestrial Networks via Expert-Driven Model Splitting</title>
      <link>https://cluster-site.onrender.com/posts/ems-fl-federated-tuning-of-mixture-of-experts-in-satellite-terrestrial-networks-via-expert-driven-model-splitting/</link>
      <pubDate>Tue, 24 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/ems-fl-federated-tuning-of-mixture-of-experts-in-satellite-terrestrial-networks-via-expert-driven-model-splitting/</guid>
      <description>• Combines Mixture‑of‑Experts (MoE) with satellite‑terrestrial networks (STN) to overcome data scarcity and compute limits in federated learning. • Introduces EMS‑FL, an expert‑dri</description>
    </item>
    <item>
      <title>Federated Learning-Assisted Optimization of Mobile Transmission with Digital Twins</title>
      <link>https://cluster-site.onrender.com/posts/federated-learning-assisted-optimization-of-mobile-transmission-with-digital-twins/</link>
      <pubDate>Tue, 24 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/federated-learning-assisted-optimization-of-mobile-transmission-with-digital-twins/</guid>
      <description>• Federated learning framework enables mobile transmission scheduling while preserving device privacy. • Three energy‑constrained problems tackled: minimize transmission time, fixe</description>
    </item>
    <item>
      <title>Federated Reasoning Distillation Framework with Model Learnability-Aware Data Allocation</title>
      <link>https://cluster-site.onrender.com/posts/federated-reasoning-distillation-framework-with-model-learnability-aware-data-allocation/</link>
      <pubDate>Tue, 24 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/federated-reasoning-distillation-framework-with-model-learnability-aware-data-allocation/</guid>
      <description>• Addresses bidirectional model learnability gap in federated LLM-SLM reasoning collaboration. • Introduces LaDa framework with learnability-aware data filter for high-reward sampl</description>
    </item>
    <item>
      <title>Replication Study: Federated Text-Driven Prompt Generation for Vision-Language Models</title>
      <link>https://cluster-site.onrender.com/posts/replication-study-federated-text-driven-prompt-generation-for-vision-language-models/</link>
      <pubDate>Tue, 24 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/replication-study-federated-text-driven-prompt-generation-for-vision-language-models/</guid>
      <description>• FedTPG introduces dynamic text-driven prompt generation for vision-language models in federated settings. • Replication evaluated on six datasets, achieving 74.58% seen, 76.00% u</description>
    </item>
    <item>
      <title>Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity</title>
      <link>https://cluster-site.onrender.com/posts/ringleader-asgd-the-first-asynchronous-sgd-with-optimal-time-complexity-under-data-heterogeneity/</link>
      <pubDate>Fri, 20 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/ringleader-asgd-the-first-asynchronous-sgd-with-optimal-time-complexity-under-data-heterogeneity/</guid>
      <description>• Introduces Ringleader ASGD, the first asynchronous SGD achieving optimal time complexity under data heterogeneity. • Eliminates unrealistic similarity assumptions across workers&#39;</description>
    </item>
    <item>
      <title>Privacy-Preserving Federated Learning - Future Collaboration and Continued Research</title>
      <link>https://cluster-site.onrender.com/posts/privacy-preserving-federated-learning-future-collaboration-and-continued-research/</link>
      <pubDate>Mon, 27 Jan 2025 12:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/privacy-preserving-federated-learning-future-collaboration-and-continued-research/</guid>
      <description>• Final NIST blog concludes US‑UK collaboration on privacy‑preserving federated learning. • Series tracks evolution from theoretical PET discussions to real‑world adoption. • Explo</description>
    </item>
    <item>
      <title>Data Pipeline Challenges of Privacy-Preserving Federated Learning</title>
      <link>https://cluster-site.onrender.com/posts/data-pipeline-challenges-of-privacy-preserving-federated-learning/</link>
      <pubDate>Thu, 05 Dec 2024 12:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/data-pipeline-challenges-of-privacy-preserving-federated-learning/</guid>
      <description>• PPFL hides raw data from training org, preventing quality assessment and format validation. • Traditional preprocessing steps are often omitted in PPFL research, focusing solely</description>
    </item>
  </channel>
</rss>
