Data-Dependent Conversion to a Compact Integer-Weighted Representation of a Weighted Voting Classifier
Data-Dependent Conversion to a Compact Integer-Weighted Representation of a Weighted Voting Classifier
复制标题
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Mitsuki Maekawa;Atsuyoshi Nakamura;Mineichi Kudo
中科院分区：
文献类型：
--
作者：
Mitsuki Maekawa;Atsuyoshi Nakamura;Mineichi Kudo
我们提出了一种将实数加权投票分类器转换为紧凑整数加权投票分类器的方法。像那些使用 boosting 训练的实加权投票分类器由于其高预测性能而非常流行和广泛使用。然而，实数非常消耗空间，并且与整数运算相比，其浮点运算速度较慢，因此紧凑的整数权重更适合在计算资源较小的设备上实现。我们的转换利用给定的特征向量并解决整数线性规划问题，该问题在保持向量分类结果不变的约束下最小化整数权重之和。根据我们使用 UCI 机器学习存储库数据集的实验结果，位表示大小减少到 5 。 2-33。 3 以内4%对于使用 AdaBoost-SAMME 学习的决策树桩的加权投票分类器，8 个数据集中的 7 个数据集的测试精度下降了 7%。
We propose a method of converting a real-weighted voting classifier to a compact integer-weighted voting classifier. Real-weighted voting classifiers like those trained using boosting are very popular and widely used due to their high prediction performance. Real numbers, however, are space-consuming and its floating-point arithmetic is slow compared to integer arithmetic, so compact integer weights are preferable for implementation on devices with small computational resources. Our conversion makes use of given feature vectors and solves an integer linear programming problem that minimizes the sum of integer weights under the constraint of keeping the classification result for the vectors unchanged. According to our experimental results using datasets of UCI Machine Learning Repository, the bit representation sizes are reduced to 5 . 2-33 . 4% within 3 . 7% test accuracy degrade in 7 of 8 datasets for the weighted voting classifiers of decision stumps learned using AdaBoost-SAMME.