Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (4): 1131-1136.DOI: 10.11772/j.issn.1001-9081.2021071264
Special Issue: CCF第36届中国计算机应用大会 (CCF NCCA 2021)
• The 36 CCF National Conference of Computer Applications (CCF NCCA 2020) • Previous Articles Next Articles
Changyin LUO1,2,3, Junyu WANG1,2,3, Xuebin CHEN1,2,3(), Chundi MA1, Shufen ZHANG1,2,3
Received:
2021-07-16
Revised:
2021-10-13
Accepted:
2021-10-18
Online:
2021-10-13
Published:
2022-04-10
Contact:
Xuebin CHEN
About author:
LUO Changyin, born in 1994, M. S. candidate. His research interests include data security.Supported by:
罗长银1,2,3, 王君宇1,2,3, 陈学斌1,2,3(), 马春地1, 张淑芬1,2,3
通讯作者:
陈学斌
作者简介:
罗长银(1994—),男,陕西安康人,硕士研究生,CCF会员,主要研究方向:数据安全基金资助:
CLC Number:
Changyin LUO, Junyu WANG, Xuebin CHEN, Chundi MA, Shufen ZHANG. Improved federated weighted average algorithm[J]. Journal of Computer Applications, 2022, 42(4): 1131-1136.
罗长银, 王君宇, 陈学斌, 马春地, 张淑芬. 改进的联邦加权平均算法[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1131-1136.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2021071264
数据集 | 样本数 | 样本维度 | 类别数 |
---|---|---|---|
digits | 5 620 | 64 | 10 |
recognition | 20 000 | 16 | 26 |
segment | 2 310 | 19 | 7 |
segmentation | 2 310 | 19 | 7 |
telescope | 19 020 | 10 | 2 |
Tab. 1 Datasets used for experiment
数据集 | 样本数 | 样本维度 | 类别数 |
---|---|---|---|
digits | 5 620 | 64 | 10 |
recognition | 20 000 | 16 | 26 |
segment | 2 310 | 19 | 7 |
segmentation | 2 310 | 19 | 7 |
telescope | 19 020 | 10 | 2 |
数据集 | 初始全局模型 | k=1 | k=2 | k=3 | |||
---|---|---|---|---|---|---|---|
准确率 | 方差/10-5 | 准确率 | 方差/10-5 | 准确率 | 方差/10-5 | ||
digits | 随机森林 | 0.962 8 | 7.25 | 0.962 3 | 6.65 | 0.962 7 | 9.38 |
朴素贝叶斯 | 0.803 8 | 167.22 | 0.799 4 | 172.74 | 0.799 3 | 175.84 | |
神经网络 | 0.956 5 | 11.50 | 0.959 2 | 10.53 | 0.958 2 | 9.15 | |
决策树 | 0.826 7 | 42.74 | 0.827 2 | 40.16 | 0.827 1 | 44.32 | |
recognition | 随机森林 | 0.901 3 | 6.41 | 0.901 8 | 5.42 | 0.901 4 | 9.27 |
朴素贝叶斯 | 0.633 2 | 21.78 | 0.634 0 | 19.37 | 0.634 2 | 20.54 | |
神经网络 | 0.839 9 | 21.01 | 0.841 0 | 11.21 | 0.841 8 | 12.18 | |
决策树 | 0.764 7 | 21.44 | 0.766 6 | 20.15 | 0.767 6 | 15.80 | |
segment | 随机森林 | 0.948 2 | 22.82 | 0.948 7 | 30.67 | 0.953 3 | 42.52 |
朴素贝叶斯 | 0.793 0 | 99.68 | 0.794 2 | 110.83 | 0.785 1 | 120.75 | |
神经网络 | 0.779 7 | 303.81 | 0.781 8 | 294.75 | 0.788 6 | 388.84 | |
决策树 | 0.925 1 | 40.52 | 0.923 7 | 45.45 | 0.920 2 | 54.10 | |
segmentation | 随机森林 | 0.950 5 | 29.26 | 0.948 0 | 31.37 | 0.951 1 | 25.40 |
朴素贝叶斯 | 0.792 2 | 110.21 | 0.793 7 | 127.75 | 0.788 9 | 165.34 | |
神经网络 | 0.782 0 | 297.72 | 0.770 5 | 452.76 | 0.789 0 | 264.45 | |
决策树 | 0.918 8 | 53.95 | 0.926 0 | 41.33 | 0.920 5 | 64.32 | |
telescope | 随机森林 | 0.866 0 | 8.34 | 0.865 4 | 5.67 | 0.865 2 | 6.49 |
朴素贝叶斯 | 0.728 1 | 14.81 | 0.726 0 | 17.78 | 0.727 5 | 16.10 | |
神经网络 | 0.812 2 | 14.83 | 0.809 5 | 19.12 | 0.811 7 | 18.19 | |
决策树 | 0.800 2 | 9.11 | 0.799 7 | 9.95 | 0.802 8 | 12.12 |
Tab. 2 Accuracy and variance of different initial global models on pre-test samples of different equal divided datasets
数据集 | 初始全局模型 | k=1 | k=2 | k=3 | |||
---|---|---|---|---|---|---|---|
准确率 | 方差/10-5 | 准确率 | 方差/10-5 | 准确率 | 方差/10-5 | ||
digits | 随机森林 | 0.962 8 | 7.25 | 0.962 3 | 6.65 | 0.962 7 | 9.38 |
朴素贝叶斯 | 0.803 8 | 167.22 | 0.799 4 | 172.74 | 0.799 3 | 175.84 | |
神经网络 | 0.956 5 | 11.50 | 0.959 2 | 10.53 | 0.958 2 | 9.15 | |
决策树 | 0.826 7 | 42.74 | 0.827 2 | 40.16 | 0.827 1 | 44.32 | |
recognition | 随机森林 | 0.901 3 | 6.41 | 0.901 8 | 5.42 | 0.901 4 | 9.27 |
朴素贝叶斯 | 0.633 2 | 21.78 | 0.634 0 | 19.37 | 0.634 2 | 20.54 | |
神经网络 | 0.839 9 | 21.01 | 0.841 0 | 11.21 | 0.841 8 | 12.18 | |
决策树 | 0.764 7 | 21.44 | 0.766 6 | 20.15 | 0.767 6 | 15.80 | |
segment | 随机森林 | 0.948 2 | 22.82 | 0.948 7 | 30.67 | 0.953 3 | 42.52 |
朴素贝叶斯 | 0.793 0 | 99.68 | 0.794 2 | 110.83 | 0.785 1 | 120.75 | |
神经网络 | 0.779 7 | 303.81 | 0.781 8 | 294.75 | 0.788 6 | 388.84 | |
决策树 | 0.925 1 | 40.52 | 0.923 7 | 45.45 | 0.920 2 | 54.10 | |
segmentation | 随机森林 | 0.950 5 | 29.26 | 0.948 0 | 31.37 | 0.951 1 | 25.40 |
朴素贝叶斯 | 0.792 2 | 110.21 | 0.793 7 | 127.75 | 0.788 9 | 165.34 | |
神经网络 | 0.782 0 | 297.72 | 0.770 5 | 452.76 | 0.789 0 | 264.45 | |
决策树 | 0.918 8 | 53.95 | 0.926 0 | 41.33 | 0.920 5 | 64.32 | |
telescope | 随机森林 | 0.866 0 | 8.34 | 0.865 4 | 5.67 | 0.865 2 | 6.49 |
朴素贝叶斯 | 0.728 1 | 14.81 | 0.726 0 | 17.78 | 0.727 5 | 16.10 | |
神经网络 | 0.812 2 | 14.83 | 0.809 5 | 19.12 | 0.811 7 | 18.19 | |
决策树 | 0.800 2 | 9.11 | 0.799 7 | 9.95 | 0.802 8 | 12.12 |
数据集 | 初始全局模型 | k=1 | k=2 | k=3 | |||
---|---|---|---|---|---|---|---|
准确率 | 方差/10-5 | 准确率 | 方差/10-5 | 准确率 | 方差/10-5 | ||
digits | 随机森林 | 0.962 4 | 10.79 | 0.962 7 | 11.69 | 0.962 3 | 9.53 |
朴素贝叶斯 | 0.798 8 | 175.32 | 0.793 7 | 219.40 | 0.798 2 | 186.67 | |
神经网络 | 0.960 2 | 11.58 | 0.957 3 | 9.47 | 0.956 6 | 11.07 | |
决策树 | 0.822 9 | 36.53 | 0.823 4 | 45.51 | 0.823 0 | 52.87 | |
recognition | 随机森林 | 0.901 3 | 5.52 | 0.901 4 | 8.40 | 0.902 7 | 6.17 |
朴素贝叶斯 | 0.633 9 | 18.13 | 0.633 9 | 19.38 | 0.632 4 | 21.41 | |
神经网络 | 0.838 9 | 24.65 | 0.838 9 | 17.84 | 0.838 58 | 19.39 | |
决策树 | 0.765 7 | 17.29 | 0.767 8 | 14.05 | 0.766 7 | 17.13 | |
segment | 随机森林 | 0.951 1 | 32.55 | 0.950 1 | 31.66 | 0.947 2 | 29.59 |
朴素贝叶斯 | 0.790 2 | 86.48 | 0.791 0 | 135.76 | 0.787 3 | 128.91 | |
神经网络 | 0.880 0 | 184.09 | 0.882 2 | 182.46 | 0.884 7 | 201.99 | |
决策树 | 0.921 9 | 55.81 | 0.922 7 | 46.23 | 0.925 0 | 42.23 | |
segmentation | 随机森林 | 0.949 7 | 34.26 | 0.948 0 | 33.65 | 0.951 5 | 24.47 |
朴素贝叶斯 | 0.786 0 | 174.30 | 0.793 5 | 120.29 | 0.792 7 | 152.34 | |
神经网络 | 0.882 7 | 201.71 | 0.878 0 | 210.58 | 0.878 0 | 233.33 | |
决策树 | 0.925 4 | 53.00 | 0.917 5 | 47.24 | 0.920 0 | 53.30 | |
telescope | 随机森林 | 0.864 7 | 8.63 | 0.865 5 | 7.81 | 0.865 5 | 9.18 |
朴素贝叶斯 | 0.725 3 | 17.59 | 0.727 4 | 13.24 | 0.725 4 | 16.77 | |
神经网络 | 0.806 5 | 29.24 | 0.808 6 | 26.64 | 0.809 5 | 21.53 | |
决策树 | 0.800 3 | 11.56 | 0.800 3 | 14.15 | 0.799 3 | 13.53 |
Tab. 3 Accuracy and variance of different initial global models on pre-test samples of different unequal divided datasets
数据集 | 初始全局模型 | k=1 | k=2 | k=3 | |||
---|---|---|---|---|---|---|---|
准确率 | 方差/10-5 | 准确率 | 方差/10-5 | 准确率 | 方差/10-5 | ||
digits | 随机森林 | 0.962 4 | 10.79 | 0.962 7 | 11.69 | 0.962 3 | 9.53 |
朴素贝叶斯 | 0.798 8 | 175.32 | 0.793 7 | 219.40 | 0.798 2 | 186.67 | |
神经网络 | 0.960 2 | 11.58 | 0.957 3 | 9.47 | 0.956 6 | 11.07 | |
决策树 | 0.822 9 | 36.53 | 0.823 4 | 45.51 | 0.823 0 | 52.87 | |
recognition | 随机森林 | 0.901 3 | 5.52 | 0.901 4 | 8.40 | 0.902 7 | 6.17 |
朴素贝叶斯 | 0.633 9 | 18.13 | 0.633 9 | 19.38 | 0.632 4 | 21.41 | |
神经网络 | 0.838 9 | 24.65 | 0.838 9 | 17.84 | 0.838 58 | 19.39 | |
决策树 | 0.765 7 | 17.29 | 0.767 8 | 14.05 | 0.766 7 | 17.13 | |
segment | 随机森林 | 0.951 1 | 32.55 | 0.950 1 | 31.66 | 0.947 2 | 29.59 |
朴素贝叶斯 | 0.790 2 | 86.48 | 0.791 0 | 135.76 | 0.787 3 | 128.91 | |
神经网络 | 0.880 0 | 184.09 | 0.882 2 | 182.46 | 0.884 7 | 201.99 | |
决策树 | 0.921 9 | 55.81 | 0.922 7 | 46.23 | 0.925 0 | 42.23 | |
segmentation | 随机森林 | 0.949 7 | 34.26 | 0.948 0 | 33.65 | 0.951 5 | 24.47 |
朴素贝叶斯 | 0.786 0 | 174.30 | 0.793 5 | 120.29 | 0.792 7 | 152.34 | |
神经网络 | 0.882 7 | 201.71 | 0.878 0 | 210.58 | 0.878 0 | 233.33 | |
决策树 | 0.925 4 | 53.00 | 0.917 5 | 47.24 | 0.920 0 | 53.30 | |
telescope | 随机森林 | 0.864 7 | 8.63 | 0.865 5 | 7.81 | 0.865 5 | 9.18 |
朴素贝叶斯 | 0.725 3 | 17.59 | 0.727 4 | 13.24 | 0.725 4 | 16.77 | |
神经网络 | 0.806 5 | 29.24 | 0.808 6 | 26.64 | 0.809 5 | 21.53 | |
决策树 | 0.800 3 | 11.56 | 0.800 3 | 14.15 | 0.799 3 | 13.53 |
数据集 | 分割方式 | 初始 全局模型 | 加权联邦 平均算法 | 传统联邦 平均算法 | ||
---|---|---|---|---|---|---|
准确率 | 方差/10-5 | 准确率 | 方差/10-5 | |||
digits | 均分 | 随机森林 | 0.963 0 | 2.49 | 0.963 0 | 2.45 |
朴素贝叶斯 | 0.809 9 | 26.26 | 0.798 6 | 31.09 | ||
神经网络 | 0.958 7 | 2.01 | 0.958 6 | 2.03 | ||
决策树 | 0.828 3 | 6.65 | 0.827 4 | 6.41 | ||
非均分 | 随机森林 | 0.963 4 | 2.04 | 0.963 4 | 2.06 | |
朴素贝叶斯 | 0.811 4 | 35.29 | 0.799 1 | 49.21 | ||
神经网络 | 0.959 3 | 1.89 | 0.959 1 | 2.02 | ||
决策树 | 0.829 2 | 6.33 | 0.828 3 | 6.23 | ||
recognition | 均分 | 随机森林 | 0.901 1 | 1.55 | 0.901 0 | 1.55 |
朴素贝叶斯 | 0.634 3 | 4.13 | 0.633 7 | 4.02 | ||
神经网络 | 0.841 2 | 2.60 | 0.840 8 | 2.56 | ||
决策树 | 0.767 8 | 3.42 | 0.767 3 | 3.50 | ||
非均分 | 随机森林 | 0.903 2 | 2.23 | 0.903 0 | 2.23 | |
朴素贝叶斯 | 0.632 9 | 4.60 | 0.632 4 | 4.43 | ||
神经网络 | 0.840 3 | 4.99 | 0.839 4 | 5.49 | ||
决策树 | 0.771 7 | 6.29 | 0.771 0 | 6.02 | ||
segment | 均分 | 随机森林 | 0.949 1 | 5.82 | 0.948 9 | 5.98 |
朴素贝叶斯 | 0.793 0 | 36.69 | 0.790 1 | 33.70 | ||
神经网络 | 0.801 6 | 77.91 | 0.787 9 | 81.88 | ||
决策树 | 0.922 8 | 8.20 | 0.922 5 | 7.85 | ||
非均分 | 随机森林 | 0.950 6 | 4.69 | 0.950 3 | 4.72 | |
朴素贝叶斯 | 0.792 4 | 37.20 | 0.788 9 | 33.31 | ||
神经网络 | 0.891 7 | 22.98 | 0.884 1 | 51.07 | ||
决策树 | 0.923 5 | 8.89 | 0.922 8 | 9.32 | ||
segmentation | 均分 | 随机森林 | 0.950 4 | 5.29 | 0.950 1 | 5.47 |
朴素贝叶斯 | 0.796 4 | 36.95 | 0.793 3 | 33.84 | ||
神经网络 | 0.794 4 | 62.31 | 0.778 4 | 73.85 | ||
决策树 | 0.921 5 | 8.28 | 0.920 9 | 7.85 | ||
非均分 | 随机森林 | 0.951 5 | 5.83 | 0.951 2 | 5.83 | |
朴素贝叶斯 | 0.794 9 | 28.47 | 0.791 8 | 29.51 | ||
神经网络 | 0.890 6 | 26.15 | 0.882 0 | 64.88 | ||
决策树 | 0.921 5 | 8.28 | 0.920 9 | 7.85 | ||
telescope | 均分 | 随机森林 | 0.865 1 | 1.36 | 0.865 1 | 1.35 |
朴素贝叶斯 | 0.726 0 | 4.22 | 0.725 9 | 4.16 | ||
神经网络 | 0.811 3 | 3.52 | 0.810 7 | 4.47 | ||
决策树 | 0.800 1 | 1.85 | 0.800 0 | 1.78 | ||
非均分 | 随机森林 | 0.868 9 | 2.62 | 0.868 9 | 2.51 | |
朴素贝叶斯 | 0.725 3 | 3.99 | 0.725 1 | 3.95 | ||
神经网络 | 0.809 1 | 4.09 | 0.807 7 | 6.53 | ||
决策树 | 0.803 9 | 3.54 | 0.803 6 | 3.37 |
Tab. 4 Accuracy comparison of weighted federated average algorithm and traditional federated average algorithm
数据集 | 分割方式 | 初始 全局模型 | 加权联邦 平均算法 | 传统联邦 平均算法 | ||
---|---|---|---|---|---|---|
准确率 | 方差/10-5 | 准确率 | 方差/10-5 | |||
digits | 均分 | 随机森林 | 0.963 0 | 2.49 | 0.963 0 | 2.45 |
朴素贝叶斯 | 0.809 9 | 26.26 | 0.798 6 | 31.09 | ||
神经网络 | 0.958 7 | 2.01 | 0.958 6 | 2.03 | ||
决策树 | 0.828 3 | 6.65 | 0.827 4 | 6.41 | ||
非均分 | 随机森林 | 0.963 4 | 2.04 | 0.963 4 | 2.06 | |
朴素贝叶斯 | 0.811 4 | 35.29 | 0.799 1 | 49.21 | ||
神经网络 | 0.959 3 | 1.89 | 0.959 1 | 2.02 | ||
决策树 | 0.829 2 | 6.33 | 0.828 3 | 6.23 | ||
recognition | 均分 | 随机森林 | 0.901 1 | 1.55 | 0.901 0 | 1.55 |
朴素贝叶斯 | 0.634 3 | 4.13 | 0.633 7 | 4.02 | ||
神经网络 | 0.841 2 | 2.60 | 0.840 8 | 2.56 | ||
决策树 | 0.767 8 | 3.42 | 0.767 3 | 3.50 | ||
非均分 | 随机森林 | 0.903 2 | 2.23 | 0.903 0 | 2.23 | |
朴素贝叶斯 | 0.632 9 | 4.60 | 0.632 4 | 4.43 | ||
神经网络 | 0.840 3 | 4.99 | 0.839 4 | 5.49 | ||
决策树 | 0.771 7 | 6.29 | 0.771 0 | 6.02 | ||
segment | 均分 | 随机森林 | 0.949 1 | 5.82 | 0.948 9 | 5.98 |
朴素贝叶斯 | 0.793 0 | 36.69 | 0.790 1 | 33.70 | ||
神经网络 | 0.801 6 | 77.91 | 0.787 9 | 81.88 | ||
决策树 | 0.922 8 | 8.20 | 0.922 5 | 7.85 | ||
非均分 | 随机森林 | 0.950 6 | 4.69 | 0.950 3 | 4.72 | |
朴素贝叶斯 | 0.792 4 | 37.20 | 0.788 9 | 33.31 | ||
神经网络 | 0.891 7 | 22.98 | 0.884 1 | 51.07 | ||
决策树 | 0.923 5 | 8.89 | 0.922 8 | 9.32 | ||
segmentation | 均分 | 随机森林 | 0.950 4 | 5.29 | 0.950 1 | 5.47 |
朴素贝叶斯 | 0.796 4 | 36.95 | 0.793 3 | 33.84 | ||
神经网络 | 0.794 4 | 62.31 | 0.778 4 | 73.85 | ||
决策树 | 0.921 5 | 8.28 | 0.920 9 | 7.85 | ||
非均分 | 随机森林 | 0.951 5 | 5.83 | 0.951 2 | 5.83 | |
朴素贝叶斯 | 0.794 9 | 28.47 | 0.791 8 | 29.51 | ||
神经网络 | 0.890 6 | 26.15 | 0.882 0 | 64.88 | ||
决策树 | 0.921 5 | 8.28 | 0.920 9 | 7.85 | ||
telescope | 均分 | 随机森林 | 0.865 1 | 1.36 | 0.865 1 | 1.35 |
朴素贝叶斯 | 0.726 0 | 4.22 | 0.725 9 | 4.16 | ||
神经网络 | 0.811 3 | 3.52 | 0.810 7 | 4.47 | ||
决策树 | 0.800 1 | 1.85 | 0.800 0 | 1.78 | ||
非均分 | 随机森林 | 0.868 9 | 2.62 | 0.868 9 | 2.51 | |
朴素贝叶斯 | 0.725 3 | 3.99 | 0.725 1 | 3.95 | ||
神经网络 | 0.809 1 | 4.09 | 0.807 7 | 6.53 | ||
决策树 | 0.803 9 | 3.54 | 0.803 6 | 3.37 |
数据集 | 模型 | 准确率 | 数据集 | 模型 | 准确率 |
---|---|---|---|---|---|
digits | 随机森林 | 0.977 8 | segmentation | 随机森林 | 0.975 3 |
朴素贝叶斯 | 0.790 0 | 朴素贝叶斯 | 0.769 7 | ||
神经网络 | 0.975 6 | 神经网络 | 0.941 1 | ||
决策树 | 0.893 9 | 决策树 | 0.963 6 | ||
recognition | 随机森林 | 0.965 9 | telescope | 随机森林 | 0.881 3 |
朴素贝叶斯 | 0.641 4 | 朴素贝叶斯 | 0.726 9 | ||
神经网络 | 0.927 4 | 神经网络 | 0.836 1 | ||
决策树 | 0.883 9 | 决策树 | 0.811 6 | ||
segment | 随机森林 | 0.978 4 | |||
朴素贝叶斯 | 0.796 5 | ||||
神经网络 | 0.955 8 | ||||
决策树 | 0.962 8 |
Tab. 5 Accuracies of models established by traditional multi-source data processing method
数据集 | 模型 | 准确率 | 数据集 | 模型 | 准确率 |
---|---|---|---|---|---|
digits | 随机森林 | 0.977 8 | segmentation | 随机森林 | 0.975 3 |
朴素贝叶斯 | 0.790 0 | 朴素贝叶斯 | 0.769 7 | ||
神经网络 | 0.975 6 | 神经网络 | 0.941 1 | ||
决策树 | 0.893 9 | 决策树 | 0.963 6 | ||
recognition | 随机森林 | 0.965 9 | telescope | 随机森林 | 0.881 3 |
朴素贝叶斯 | 0.641 4 | 朴素贝叶斯 | 0.726 9 | ||
神经网络 | 0.927 4 | 神经网络 | 0.836 1 | ||
决策树 | 0.883 9 | 决策树 | 0.811 6 | ||
segment | 随机森林 | 0.978 4 | |||
朴素贝叶斯 | 0.796 5 | ||||
神经网络 | 0.955 8 | ||||
决策树 | 0.962 8 |
数据集 | 模型 | 准确率 | 数据集 | 模型 | 准确率 |
---|---|---|---|---|---|
digits | 随机森林 | 0.974 4 | segmentation | 随机森林 | 0.964 1 |
朴素贝叶斯 | 0.750 9 | 朴素贝叶斯 | 0.770 1 | ||
神经网络 | 0.970 3 | 神经网络 | 0.882 3 | ||
决策树 | 0.879 8 | 决策树 | 0.936 8 | ||
recognition | 随机森林 | 0.940 2 | telescope | 随机森林 | 0.866 2 |
朴素贝叶斯 | 0.600 8 | 朴素贝叶斯 | 0.729 7 | ||
神经网络 | 0.810 7 | 神经网络 | 0.646 2 | ||
决策树 | 0.682 5 | 决策树 | 0.828 4 | ||
segment | 随机森林 | 0.966 0 | |||
朴素贝叶斯 | 0.773 8 | ||||
神经网络 | 0.859 2 | ||||
决策树 | 0.937 3 |
Tab. 6 Accuracies of models established by the improved federated average algorithm based on analytic hierarchy process
数据集 | 模型 | 准确率 | 数据集 | 模型 | 准确率 |
---|---|---|---|---|---|
digits | 随机森林 | 0.974 4 | segmentation | 随机森林 | 0.964 1 |
朴素贝叶斯 | 0.750 9 | 朴素贝叶斯 | 0.770 1 | ||
神经网络 | 0.970 3 | 神经网络 | 0.882 3 | ||
决策树 | 0.879 8 | 决策树 | 0.936 8 | ||
recognition | 随机森林 | 0.940 2 | telescope | 随机森林 | 0.866 2 |
朴素贝叶斯 | 0.600 8 | 朴素贝叶斯 | 0.729 7 | ||
神经网络 | 0.810 7 | 神经网络 | 0.646 2 | ||
决策树 | 0.682 5 | 决策树 | 0.828 4 | ||
segment | 随机森林 | 0.966 0 | |||
朴素贝叶斯 | 0.773 8 | ||||
神经网络 | 0.859 2 | ||||
决策树 | 0.937 3 |
1 | 朱骁, 杨庚. 横向联邦学习中PCA差分隐私数据发布算法[J]. 计算机应用研究,2022,39(1):236-239,248. |
ZHU X, YANG G. PCA differential privacy data publishing algorithm[J]. Application Research Of Computers,2022,39(1):236-239,248. | |
2 | LI W K, LU S R, DENG D L. Quantum federated learning through blind quantum computing[J]. Science China Physics, Mechanics & Astronomy, 2021, 64: 100312. 10.1007/s11433-021-1753-3 |
3 | XU, J L, LIN J, LIANG W, et al. Privacy preserving personalized blockchain reliability prediction via federated learning in IoT environments[J]. Cluster Computing, 2021, 9(2): 1-12. 10.1007/s10586-021-03399-w |
4 | XING J, TIAN J D, JIANG Z X, et al. Jupiter: a modern federated learning platform for regional medical care[J]. Science China Information Sciences, 2021, 64(10):202101:1-202101:14. 10.1007/s11432-020-3062-8 |
5 | 刘俊旭,孟小峰.机器学习的隐私保护研究综述[J].计算机研究与发展,2020,57(2):346-362. 10.7544/issn1000-1239.2020.20190455 |
LIU J X, MENG X F. Review on privacy protection of machine learning [J]. Journal of Computer Research and Development, 2020,57 (2): 346-362. 10.7544/issn1000-1239.2020.20190455 | |
6 | POLAP D, WOZNIAK M. Meta-heuristic as manager in federated learning approaches for image processing purposes [J]. Applied Soft Computing, 2021,113(PART A): 107872. 10.1016/j.asoc.2021.107872 |
7 | ZHU H Y, XU J J, LIU S Q, et al. Federated learning on non-IID data: a survey[J]. Neurocomputing, 2021, 465:371-390. 10.1016/j.neucom.2021.07.098 |
8 | LIU J C, WANG J H, RONG C H, et al. FedPA: an adaptively partial model aggregation strategy in federated learning[J]. Computer Networks, 2021, 199: 108468. 10.1016/j.comnet.2021.108468 |
9 | 罗长银, 陈学斌, 马春地, 等. 面向区块链的在线联邦增量学习算法[J]. 计算机应用, 2021, 41(2):363-371. 10.11772/j.issn.1001-9081.2020050609 |
LUO C Y, CHEN X B, MA C D, et al. Online federated incremental learning algorithm for blockchain[J]. Journal of Computer Applications, 2021, 41(2):363-371. 10.11772/j.issn.1001-9081.2020050609 | |
10 | CHEN Y, SUN X Y, JIN Y C. Communication-efficient federated deep learning with layerwise asynchronous model update and temporally weighted aggregation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 31(10):4229-4238. 10.1109/tnnls.2019.2953131 |
11 | BLANCO-JUSTICIA A, DOMINGO-FERRER J, MARTÍNEZ S, et al. Achieving security and privacy in federated learning systems: survey, research challenges and future directions[J]. Engineering Applications of Artificial Intelligence, 2021, 106: 104468. 10.1016/j.engappai.2021.104468 |
12 | 杨强.联邦学习:人工智能的最后一公里[J].智能系统学报,2020,15(1):183-186. 10.11992/tis.202005036 |
YANG Q. Federated learning: the last mile of artificial intelligence [J] CAAI Transactions on Intelligent Systems, 2020,15 (1): 183-186. 10.11992/tis.202005036 | |
13 | 郭方方, 潮洛蒙, 朱建文. 基于相似连接的多源数据并行预处理方法[J]. 计算机应用, 2019, 39(1):57-60. 10.11772/j.issn.1001-9081.2018071869 |
GUO F F, CHAO L M, ZHU J W. Multi-source data parallel preprocessing method based on similar connection[J].Journal of Computer Applications, 2019, 39(1):57-60. 10.11772/j.issn.1001-9081.2018071869 | |
14 | GAO H H, HUANG W Q, DUAN Y C, et al. Research on cost-driven services composition in an uncertain environment[J]. Journal of Internet Technology, 2019, 20(3):755-769. |
15 | MA X, WEN C L. An asynchronous quasi-cloud/edge/client collaborative federated learning mechanism for fault diagnosis[J]. Chinese Journal of Electronics, 2021, 30(5):969-977. 10.1049/cje.2021.07.008 |
16 | ZHOU Y H, QING Y, LV J C. Communication-efficient federated learning with compensated overlap-FedAvg[J]. IEEE Transactions On Neural Networks and Learning Systems, 2020, 33 (1) :192-205. |
17 | 罗长银, 陈学斌, 马春地, 等. 基于层析分析改进的联邦平均算法[J]. 计算机科学, 2021, 48(8):32-40. 10.11896/jsjkx.201000093 |
LUO C Y, CHEN X B, MA C D, et al. Improved federated average algorithm based on tomographic analysis[J]. Computer Science, 2021, 48(8):32-40. 10.11896/jsjkx.201000093 | |
18 | KANG D, AHN C W. Communication cost reduction with partial structure in federated learning[J]. Electronics, 2021, 10(17):2081. 10.3390/electronics10172081 |
19 | LIU J C, XU H L, XU Y, et al. Communication-efficient asynchronous federated learning in resource-constrained edge computing[J]. Networks, 2021, 199(9): 108429. 10.1016/j.comnet.2021.108429 |
20 | XU J J, DU W L, XU Q Y, et al. Federated learning based atmospheric source term estimation in urban environments[J]. Computers & Chemical Engineering. 2021, 155: 107505. 10.1016/j.compchemeng.2021.107505 |
[1] | Tingwei CHEN, Jiacheng ZHANG, Junlu WANG. Random validation blockchain construction for federated learning [J]. Journal of Computer Applications, 2024, 44(9): 2770-2776. |
[2] | Zheyuan SHEN, Keke YANG, Jing LI. Personalized federated learning method based on dual stream neural network [J]. Journal of Computer Applications, 2024, 44(8): 2319-2325. |
[3] | Xuebin CHEN, Zhiqiang REN, Hongyang ZHANG. Review on security threats and defense measures in federated learning [J]. Journal of Computer Applications, 2024, 44(6): 1663-1672. |
[4] | Wei LUO, Jinquan LIU, Zheng ZHANG. Dual vertical federated learning framework incorporating secret sharing technology [J]. Journal of Computer Applications, 2024, 44(6): 1872-1879. |
[5] | Hongtao SONG, Jiangsheng YU, Qilong HAN. Industrial multivariate time series data quality assessment method [J]. Journal of Computer Applications, 2024, 44(6): 1743-1750. |
[6] | Sunjie YU, Hui ZENG, Shiyu XIONG, Hongzhou SHI. Incentive mechanism for federated learning based on generative adversarial network [J]. Journal of Computer Applications, 2024, 44(2): 344-352. |
[7] | Zucuan ZHANG, Xuebin CHEN, Rui GAO, Yuanhuai ZOU. Federated learning client selection method based on label classification [J]. Journal of Computer Applications, 2024, 44(12): 3759-3765. |
[8] | Xuebin CHEN, Changsheng QU. Overview of backdoor attacks and defense in federated learning [J]. Journal of Computer Applications, 2024, 44(11): 3459-3469. |
[9] | Shuaihua ZHANG, Shufen ZHANG, Mingchuan ZHOU, Chao XU, Xuebin CHEN. Malicious traffic detection model based on semi-supervised federated learning [J]. Journal of Computer Applications, 2024, 44(11): 3487-3494. |
[10] | Jie WU, Xuezhong QIAN, Wei SONG. Personalized federated learning based on similarity clustering and regularization [J]. Journal of Computer Applications, 2024, 44(11): 3345-3353. |
[11] | Chunyong YIN, Yongcheng ZHOU. Automatically adjusted clustered federated learning for double-ended clustering [J]. Journal of Computer Applications, 2024, 44(10): 3011-3020. |
[12] | Hui ZHOU, Yuling CHEN, Xuewei WANG, Yangwen ZHANG, Jianjiang HE. Deep shadow defense scheme of federated learning based on generative adversarial network [J]. Journal of Computer Applications, 2024, 44(1): 223-232. |
[13] | Mengjie LAN, Jianping CAI, Lan SUN. Self-regularization optimization methods for Non-IID data in federated learning [J]. Journal of Computer Applications, 2023, 43(7): 2073-2081. |
[14] | Wanzhen CHEN, En ZHANG, Leiyong QIN, Shuangxi HONG. Privacy-preserving federated learning algorithm based on blockchain in edge computing [J]. Journal of Computer Applications, 2023, 43(7): 2209-2216. |
[15] | Shangjing LIN, Ji MA, Bei ZHUANG, Yueying LI, Ziyi LI, Tie LI, Jin TIAN. Wireless traffic prediction based on federated learning [J]. Journal of Computer Applications, 2023, 43(6): 1900-1909. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||