【论文阅读】Twin neural network regression is a semi- supervised regression algorithm

TwinNeuralNetworkRegression(TNNR)是一种预测数据点间目标值差异的算法，适用于半监督回归问题。通过集成预测差异，可以提高对原始回归问题的预测准确性。文章提出了结合有标签和无标签数据的损失函数，包括均方误差损失和循环损失，并展示了这种方法在增强TNNR性能方面的潜力。实验部分探讨了不同参数和循环类型对结果的影响。

论文下载
 GitHub
bib:

@ARTICLE{
   
   WetzelMelko2022Twin,
	title 		= {
   
   Twin neural network regression is a semi- supervised regression algorithm},
	author 		= {
   
   Sebastian J Wetzel and Roger G Melko and Isaac Tamblyn},
	journal 	= {
   
   Machine Learning: Science and Technology},
	year 		= {
   
   2022},
	volume 		= {
   
   3},
	number 		= {
   
   4},
	pages 	    = {
   
   045007},
	doi         = {
   
   10.1088/2632-2153/ac9885}
}

1. 摘要

Twin neural network regression (TNNR) is trained to predict differences between the target values of two different data points rather than the targets themselves.

TNNR是作者以前的工作，但是针对回归问题的，这篇论文针对的是半监督回归（semi-supervised regression）。

By ensembling predicted differences between the targets of an unseen data point and all training data points, it is possible to obtain a very accurate prediction for the original regression problem.

通过集成未见过的数据点的目标与所有训练数据点之间的预测差异，可以获得对原始回归问题的非常准确的预测。这一步应该是描述对于不同差异的平均操作。

Since any loop of predicted differences should sum to zero, loops can be supplied to the training data, even if the data points themselves within loops are unlabelled.

loop of predicted differences should sum to zero 这一步在上一篇论文中有介绍。

Semi-supervised training improves TNNR performance, which is already state of the art, significantly.

Note:
前置工作《Twin Neural Network Regression》。这篇工作是原作者方法对于半监督学习方向的拓展。

2. 算法描述

在这里插入图片描述

$\begin{aligned} y_j^{pre}&= \frac{1}{m}\sum_{i=1}^{m}((F(x_j, x_i^{train}) + y_i^{traian})\\ &= \frac{1}{m}\sum_{i=1}^{m}((\frac{1}{2}F(x_j, x_i^{train}) + \frac{1}{2}F(x_i^{train}, x_j) + y_i^{traian})\\ \end{aligned}\tag{1}$