報(bào)告題目：Improving Training Efficiency and Quality in Federated Learning

報(bào)告時(shí)間：2023年4月18日16:00

報(bào)告地點(diǎn)：437bwin必贏國際官網(wǎng)B404

報(bào)告人：何黎剛

報(bào)告人國籍：英國

報(bào)告人單位：The University of Warwick

報(bào)告人簡介：何黎剛，博士本科和碩士畢業(yè)于華中科技大學(xué)（碩士師從韓宗芬教授和金海教授）。博士畢業(yè)于英國華威大學(xué)計(jì)算機(jī)系，并在劍橋大學(xué)進(jìn)行博士后研究?，F(xiàn)為華威大學(xué)計(jì)算機(jī)系Reader（英國大學(xué)副教授和正教授之間的一個(gè)職稱）。主要研究方向?yàn)椴⑿蟹植际教幚恚植际紸I和大數(shù)據(jù)處理。在國際期刊和會(huì)議上發(fā)表論文180余篇，主持和承擔(dān)過英國、歐盟及企業(yè)界多個(gè)研究項(xiàng)目。

報(bào)告摘要：In this talk, three piece of work we have conducted in FL will be presented. First, a semi-asynchronous FL protocol called SAFA is presented to improve the training efficiency of FL. Second, A FL scheme called hybridFL is presented. HybridFL further enhances the efficiency of SAFA by taking the reliability of FL clients into account. Moreover, hybridFL extends SAFA from a two-layer (i.e., client/server) FL scheme to a three-layer one in mobile-edge-cloud systems, enabling the support of even larger-scale FL training. Finally, in hybridFL, the clients are randomly selected to participate in FL training. If some clients have low quality data, the fact that they have equal opportunities to contribute to the final model may hurt the model quality. To address this issue, a selective FL scheme is proposed, in which data quality can be quantified and the clients with lower-quality data have fewer chances to be selected for training.

邀請人：杜博、鄭志高