Trying to Outrun Causality with Machine Learning: Limitations of Model Explainability Techniques for Identifying Predictive Variables

• URL: http://arxiv.org/abs/2202.09875v3
• Date: Wed, 23 Feb 2022 15:57:50 GMT
• Title: Trying to Outrun Causality with Machine Learning: Limitations of Model Explainability Techniques for Identifying Predictive Variables
• Authors: Matthew J. Vowels
• Abstract summary: We show that machine learning algorithms are not as flexible as they might seem, and are instead incredibly sensitive to the underling causal structure in the data. We provide some alternative recommendations for researchers wanting to explore the data for important variables.
• Score: 7.106986689736828
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine Learning explainability techniques have been proposed as a means of `explaining' or interrogating a model in order to understand why a particular decision or prediction has been made. Such an ability is especially important at a time when machine learning is being used to automate decision processes which concern sensitive factors and legal outcomes. Indeed, it is even a requirement according to EU law. Furthermore, researchers concerned with imposing overly restrictive functional form (e.g. as would be the case in a linear regression) may be motivated to use machine learning algorithms in conjunction with explainability techniques, as part of exploratory research, with the goal of identifying important variables which are associated with an outcome of interest. For example, epidemiologists might be interested in identifying 'risk factors' - i.e., factors which affect recovery from disease - by using random forests and assessing variable relevance using importance measures. However, and as we aim to demonstrate, machine learning algorithms are not as flexible as they might seem, and are instead incredibly sensitive to the underling causal structure in the data. The consequences of this are that predictors which are, in fact, critical to a causal system and highly correlated with the outcome, may nonetheless be deemed by explainability techniques to be unrelated/unimportant/unpredictive of the outcome. Rather than this being a limitation of explainability techniques per se, it is rather a consequence of the mathematical implications of regressions, and the interaction of these implications with the associated conditional independencies of the underlying causal structure. We provide some alternative recommendations for researchers wanting to explore the data for important variables.

Related papers

• Detection and Evaluation of bias-inducing Features in Machine learning [14.045499740240823]
  In the context of machine learning (ML), one can use cause-to-effect analysis to understand the reason for the biased behavior of the system. We propose an approach for systematically identifying all bias-inducing features of a model to help support the decision-making of domain experts.
  arXiv  Detail & Related papers  (2023-10-19T15:01:16Z)
• Causal Entropy and Information Gain for Measuring Causal Control [0.22252684361733285]
  We introduce causal versions of entropy and mutual information, termed causal entropy and causal information gain. These quantities capture changes in the entropy of a variable resulting from interventions on other variables. Fundamental results connecting these quantities to the existence of causal effects are derived.
  arXiv  Detail & Related papers  (2023-09-14T13:25:42Z)
• Nonlinearity, Feedback and Uniform Consistency in Causal Structural Learning [0.8158530638728501]
  Causal Discovery aims to find automated search methods for learning causal structures from observational data. This thesis focuses on two questions in causal discovery: (i) providing an alternative definition of k-Triangle Faithfulness that (i) is weaker than strong faithfulness when applied to the Gaussian family of distributions, and (ii) under the assumption that the modified version of Strong Faithfulness holds.
  arXiv  Detail & Related papers  (2023-08-15T01:23:42Z)
• A Causal Framework for Decomposing Spurious Variations [68.12191782657437]
  We develop tools for decomposing spurious variations in Markovian and Semi-Markovian models. We prove the first results that allow a non-parametric decomposition of spurious effects. The described approach has several applications, ranging from explainable and fair AI to questions in epidemiology and medicine.
  arXiv  Detail & Related papers  (2023-06-08T09:40:28Z)
• On Learning Necessary and Sufficient Causal Graphs [29.339455706346193]
  In practice, only a small subset of variables in the graph are relevant to the outcomes of interest. We propose learning a class of necessary and sufficient causal graphs (NSCG) that exclusively comprises causally relevant variables for an outcome of interest. We develop a necessary and sufficient causal structural learning (NSCSL) algorithm, by establishing theoretical properties and relationships between probabilities of causation and natural causal effects of features.
  arXiv  Detail & Related papers  (2023-01-29T08:19:15Z)
• Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability [82.29775890542967]
  Estimating personalized effects of treatments is a complex, yet pervasive problem. Recent developments in the machine learning literature on heterogeneous treatment effect estimation gave rise to many sophisticated, but opaque, tools. We use post-hoc feature importance methods to identify features that influence the model's predictions.
  arXiv  Detail & Related papers  (2022-06-16T17:59:05Z)
• Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning [76.00395335702572]
  A central goal for AI and causality is the joint discovery of abstract representations and causal structure. Existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs. In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them.
  arXiv  Detail & Related papers  (2021-07-02T05:44:56Z)
• The Causal Neural Connection: Expressiveness, Learnability, and Inference [125.57815987218756]
  An object called structural causal model (SCM) represents a collection of mechanisms and sources of random variation of the system under investigation. In this paper, we show that the causal hierarchy theorem (Thm. 1, Bareinboim et al., 2020) still holds for neural models. We introduce a special type of SCM called a neural causal model (NCM), and formalize a new type of inductive bias to encode structural constraints necessary for performing causal inferences.
  arXiv  Detail & Related papers  (2021-07-02T01:55:18Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)
• Bayesian Model Averaging for Data Driven Decision Making when Causality is Partially Known [0.0]
  We use ensemble methods like Bayesian Model Averaging (BMA) to infer set of causal graphs. We provide decisions by computing the expected value and risk of potential interventions explicitly.
  arXiv  Detail & Related papers  (2021-05-12T01:55:45Z)
• Estimating Structural Target Functions using Machine Learning and Influence Functions [103.47897241856603]
  We propose a new framework for statistical machine learning of target functions arising as identifiable functionals from statistical models. This framework is problem- and model-agnostic and can be used to estimate a broad variety of target parameters of interest in applied statistics. We put particular focus on so-called coarsening at random/doubly robust problems with partially unobserved information.
  arXiv  Detail & Related papers  (2020-08-14T16:48:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.