Causal Feature Selection

By Isabelle M Guyon, Constantin F. Aliferis, Andre´ Elisseeﬀ. 2007

153 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Causality for Machine Learning (2019, methodology): “This development has been championed by Isabelle Guyon whom (along with Andre Elisseeff) I had known from my previous work on kernel methods, and who had moved into causality through her interest in feature selection (Guyon et al., 2007).”
Visual Causal Feature Learning (2014, methodology): “We emphasize the difference between our method of causal feature learning and methods for causal feature selection (Guyon et al., 2007; Pellet and Elisseeff, 2008).”
Causal Regularization (2017, methodology): “Using the causality detection methods in the previous section for causal variable selection (Guyon et al., 2007; Cawley, 2008; Bontempi and Meyer, 2010; Sun et al., 2015) makes the variable selection process becomes very sensitive to small changes in the joint distribution of variables and may…”
Decoding brain states from fMRI connectivity graphs (2011, background): “Finally, we mention that univariate feature selection is limited because features might be individually irrelevant but provide discrimination when used together (Guyon et al., 2007).”
Causality : Objectives and Assessment (2010, background): “- Determine a local causal region around a response/target variable (causal adjacency).”
Connectionist multivariate density-estimation and its application to speech synthesis (2016, background): “Also, given domain knowledge about the causal relationship of the variables modelled, a heuristic ordering of the variables, in which causes precede effects can be expected to be easier to model (Guyon et al., 2007).”
A review of feature selection methods based on mutual information (2013, unknown): “[25] investigated causal feature selection.”
Highly Comparative Feature-Based Time-Series Classification (2014, methodology): “Many methods have been developed for performing feature selection [33–35], including the Lasso [36] and recursive feature elimination [37].”