PulseAugur
EN
LIVE 22:05:45

Federated learning research tackles quantization, fairness, and noise · 4 sources tracked

By PulseAugur Editorial · [4 sources] ·

This cluster of research papers explores advancements in federated learning (FL), a method for distributed intelligence that preserves data privacy. One paper offers a comprehensive review of quantization techniques to address FL's scalability issues, such as communication bottlenecks and device heterogeneity. Another introduces FAIRVAR, a novel variance-regularization method to improve fairness by reducing performance disparities across clients. A third paper proposes VRA-FedSGD, an algorithm designed to handle heavy-tailed gradient and communication noise prevalent in large-scale FL deployments, particularly for IoT devices. AI

IMPACT These papers advance federated learning techniques, addressing key challenges in scalability, fairness, and noise handling for real-world applications.

RANK_REASON Cluster consists of multiple academic papers on federated learning published on arXiv.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

Federated learning research tackles quantization, fairness, and noise · 4 sources tracked

COVERAGE [4]

  1. arXiv cs.LG TIER_1 English(EN) · Farwa Ikram, Dipanwita Thakur, Antonella Guzzo, Giancarlo Fortino ·

    Quantization in Federated Learning: Methods, Challenges and Future Directions

    arXiv:2606.26822v1 Announce Type: new Abstract: Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally constrained by communication bottlenecks, device heterogeneity, and the challenges…

  2. arXiv cs.LG TIER_1 English(EN) · Giancarlo Fortino ·

    Quantization in Federated Learning: Methods, Challenges and Future Directions

    Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally constrained by communication bottlenecks, device heterogeneity, and the challenges of training under statistically non-IID data. Q…

  3. arXiv cs.LG TIER_1 English(EN) · Zahra Kharaghani, Ali Dadras, Tommy L\"ofstedt ·

    FAIRVAR: Fair Federated Learning via Variance Regularization

    arXiv:2508.12042v3 Announce Type: replace Abstract: Federated learning (FL) allows collaborative training of machine learning models across multiple parties without sharing raw data. However, heterogeneous data can cause some clients to have disproportionate influence on the glob…

  4. arXiv cs.LG TIER_1 English(EN) · Yongchao Liu ·

    Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm

    Federated learning (FL) is an emerging distributed machine learning paradigm that enables local devices to jointly train a global model while keeping data decentralized and private. We propose a variance-reduction based algorithm, VRA-FedSGD, for FL in the presence of heavy-taile…

RELATED ENTITIES

RELATED TOPICS