基于PaddleFL联邦学习框架的学生学习数据隐私计算模型构建

Construction of Student Learning Data Privacy Computing Model Based on PaddleFL Federal Learning Framework

基于联邦学习框架,对高职计算机专业在校生的学习数据和毕业后的就业进行研究,运用PaddleFL横向联邦学习进行隐私计算。结果显示,在保证了数据隐私的条件下进行数据联合分析,可以对数据集进行有效训练及预测,证明通过联邦学习框架进行高校数据的多方联合计算和分析是可行的。

Based on the federal learning framework,this paper studies the learning data and employment of higher vocational students majoring in computer,and uses PaddleFL horizontal federal learning for privacy calculation.Through the comparison of results,data joint analysis is carried out under the condition of ensuring data privacy,and we can effectively train and predict the data set.It is proved that the multi-party joint calculation and analysis of university data through the federal learning framework is feasible.