Exploring Causal Relationships with Streaming Features

Abstract

Causal discovery is highly desirable in science and technology. In this paper, we study a new research problem of discovery of causal relationships in the context of streaming features, where the features steam in one by one. With a Bayesian network to represent causal relationships, we propose a novel algorithm called causal discovery from streaming features (CDFSF) which consists of a two-phase scheme. In the first phase, CDFSF dynamically discovers causal relationships between each feature seen so far with an arriving feature, while in the second phase CDFSF removes the false positives of each arrived feature from its current set of direct causes and effects. To improve the efficiency of CDFSF, using the symmetry properties between parents (causes) and children (effects) in a faithful Bayesian network, we present a variant of CDFSF, S-CDFSF. Experimental results validate our algorithms in comparison with the existing algorithms of causal relationship discovery.

Bayesian network structure learning with improved genetic algorithm

“…Chu et al 9 proposed causal time‐varying dynamic Bayesian network (cTVDBN) to efficiently discover the structure of trajectory‐based networks. Yu et al 10 proposed causal discovery from streaming features (CDFSF) and its variant–S‐CDFSF and conducted experiments on some large networks, such as Gene (801 nodes). Zhou et al 11 proposed a causal discovery algorithm to discover causal rules in large databases.…”

Markov Boundary Discovery Based on Variant Ridge Regularized Linear Models

“…Discovering causal relationships among variables from observation data sets is fundamental to the discipline, such as computer science, medicine, statistics, economics and social science [1]- [4]. Moreover, the causal relationships have been widely accepted as an alternative to randomized controlled trials(RCTs) [5]- [7]. In most cases, RCTs are impractical to discover causal relationship from the observational data due to expensive, unethical or impossible [8]- [10].…”