Flow Feature-Based Causal Structure Learning Method

Abstract

The invention discloses a causal structure learning method based on stream features, which is characterized by the following steps: 1. Generate new features with arbitrary distribution in a stream manner; 2. Perform correlation analysis on each newly generated feature ; 3. Carry out redundancy check analysis on the feature set; 4. Carry out search orientation based on each feature. Repeat steps 1, 2, 3, and 4 until the number of features generated exceeds the limit value, and finally the corresponding causal structure can be obtained. The invention can discover the implicit causal structure relationship from the linear arbitrary distribution data with flow characteristics, and at the same time reduce the time complexity of learning, so as to meet the timeliness requirement of online learning.

Description

technical field [0001] The invention belongs to the field of data mining, in particular to a flow feature-based causal structure learning method for linear arbitrary distribution data. Background technique [0002] With the progress of society and the development of science and technology, the things people need to know become more and more complex. The causal relationship within the system exists objectively. The causal structure learning is to mine the causal structural relationship contained in the data, which can help people understand the complex The nature and laws of things. Causal structure learning has penetrated into various disciplines such as biology, medicine, economics, automatic control, and information processing, and involves various aspects such as daily life, industrial production, and military defense. [0003] The distribution of many variables in real life is often non-Gaussian. For example: the values ​​of magnetoencephalographic (MEG, magnetoencepha...

AI Technical Summary

Problems solved by technology

[0006] The current classical causal structure learning methods cannot effectively deal with continuous data with linear and arbitrary distributions with flow characteristics. The main limitations of these methods include:

[0007] (1) Most of the linear arbitrary distribution-oriented structural learning algorithms are methods based on dependency analysis. In order to determine whether two features are related, this method needs to perform independence tests on a large number of subsets, resulting in the need for more independence tests. Therefore, it takes a lot of time and the computational complexity is relatively large;

[0008] (2) The structure learning algorithm for linear arbitrary distribution generally assumes that all data can be obtained in advance, and cannot process data with flow characteristics, that is, the features flow in one by one, so it cannot effectively deal with the causal structure learning problem in the dynamic and unknown feature space.

Images