Causal Interpretability for Machine Learning - Problems, Methods and Evaluation

By Raha Moraffah, Mansooreh Karami, Ruocheng Guo, Adrienne Jeanisha Raglin, Huan Liu. 2020

266 citations recorded by the source corpus.

Machine learning models have had discernible achievements in a myriad of applications. However, most of these models are black-boxes, and it is obscure how the decisions are made by them. This makes the models unreliable and untrustworthy. To provide insights into the decision making processes of these models, a variety of traditional interpretable models have been proposed. Moreover, to generate more humanfriendly explanations, recent work on interpretability tries to answer questions related to causality such as "Why does this model makes such decisions?" or "Was it a specific feature that caused the decision made by the model?". In this work, models that aim to answer causal questions are referred to as causal interpretable models. The existing surveys have covered concepts and methodologies of traditional interpretability. In this work, we present a comprehensive survey on causal interpretable models from the aspects of the problems and methods. In addition, this survey provides in-depth insights into the existing evaluation metrics for measuring interpretability, which can help practitioners understand for what scenarios each evaluation metric is suitable.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Causal Inference & Discovery

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

In Safety, Robustness & Interpretability

In Causal Inference & Discovery

Citations in the corpus

Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, methodology): “In addition, according to a recent survey on causal interpretability for ML [55], it has been highlighted the absence of ground truth data for causal explanations and verification of causal relationships make evaluating causal”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, background): “Some surveys discuss evaluation as part of a broader review of XAI methods [1, 29, 32, 59, 81, 120, 170, 173, 175, 182, 303], or mainly discuss evaluation with user studies [52, 100, 136, 170].”
A Survey of Learning Causality with Data (2018, background): “Potential research directions include: (1) causal interpretation of black box deep learning algorithms [105], (2) learning causality-aware models for robustness [9] and fairness [85].”
Generative causal explanations of black-box classifiers (2020, background): “Because explanation methods seek to answer “why” and “how” questions that use the language of cause and effect [3, 4], causal reasoning has played an increasingly important role in designing explanation frameworks [5].”
A Tutorial On the design, experimentation and application of metaheuristic algorithms to real-World optimization problems (2021, background): “Causal analysis for machine learning models [150, 151] can take a step further in this direction, discriminating which decision variables, when modiﬁed throughout the search, lead to major changes in the ﬁtness value.”
Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond (2021, background): “Using counterfactual examples to explain the model behaviors can also be included in causal inference [126], which is considered as a newperspective formodel interpretability [120, 179].”