Transaction

jmetaB0248d6aa259c9e9284ece509e4e3452fa5e333de92dcd0354cc5e27a23ae5bedbb@f9851c2160f6d07cecd53064b44b75ae180251462771b97e11dbfad2c8f6cbe5rss.itemmetarss.netM<item> <title>GPFL: A Gradient Projection-Based Client Selection Framework for Efficient Federated Learning</title> <link>https://arxiv.org/abs/2403.17833</link> <description>arXiv:2403.17833v2 Announce Type: replace-cross Abstract: Federated learning client selection is crucial for determining participant clients while balancing model accuracy and communication efficiency. Existing methods have limitations in handling data heterogeneity, computational burdens, and independent client treatment. To address these challenges, we propose GPFL, which measures client value by comparing local and global descent directions. We also employ an Exploit-Explore mechanism to enhance performance. Experimental results on FEMINST and CIFAR-10 datasets demonstrate that GPFL outperforms baselines in Non-IID scenarios, achieving over 9\% improvement in FEMINST test accuracy. Moreover, GPFL exhibits shorter computation times through pre-selection and parameter reuse in federated learning.</description> <guid isPermaLink="false">oai:arXiv.org:2403.17833v2</guid> <category>cs.LG</category> <category>cs.DC</category> <arxiv:announce_type>replace-cross</arxiv:announce_type> <dc:rights>http://creativecommons.org/licenses/by/4.0/</dc:rights> <dc:creator>Shijie Na, Yuzhi Liang, Siu-Ming Yiu</dc:creator> </item>