Complex machine learning model interpreting method and device based on local linearization

Abstract

The invention provides a complex machine learning model interpreting method and device based on local linearization, and the method comprises the steps: collecting any one point in a sample set as a sample point, and carrying out the random sampling of a plurality of sampling points around the sample point; obtaining the Euler distance between the sample point and each sampling point in an expression space, so as to enable the Euler distances to serve as the weights of the sampling points; obtaining the difference between a to-be-interpreted machine learning model and the fitting result of an interpretation function according to the weight of each sampling point and a linear model, so as to obtain an optimizing problem; carrying out the optimization solving of a linear regression problem employing a regularization penalty factor in the optimizing problem, and obtaining an interpretation result. The method can achieve the interpretation of a complex machine learning model in the neighborhood of each data point, gives full consideration to the local characteristics of a sample space, can effectively find the main features of different regions of the sample space, is more visual and convenient, and can be used for the interpretation of various types of machine learning models.

Description

technical field [0001] The invention relates to the technical field of machine learning application and analysis, in particular to a method and device for explaining complex machine learning models based on local linearization. Background technique [0002] At the beginning of the field of machine learning, researchers began to explore the interpretation (Interpretability / Comprehensibility) of machine learning algorithms. The so-called "interpretation" here is the meaning of the field of machine learning, which aims to provide a quantitative understanding of the relationship between input variables and model output. Researchers generally believe that the accuracy, complexity and interpretability of the model are inversely related, that is, the simple model has strong interpretability, but the accuracy is low; while the complex model can obtain high calculation accuracy, but it is difficult to explain intuitively. [0003] At present, researchers prefer to use complex models...

AI Technical Summary

Problems solved by technology

In summary, the interpretation methods in related technologies use simple models such as linear models and decision tree models to explain complex models in the entire input space, but cannot consider the local characteristics of the input space, which is the biggest problem in the interpretation methods in related technologies. Room for improvement

Images