On Understanding the Influence of Controllable Factors with a Feature Attribution Algorithm: a Medical Case Study
Not on the map. Why?
Abstract (arXiv)
Feature attribution XAI algorithms enable their users to gain insight into the underlying patterns of large datasets through their feature importance calculation. Existing feature attribution algorithms treat all features in a dataset homogeneously, which may lead to misinterpretation of consequences of changing feature values. In this work, we consider partitioning features into controllable and uncontrollable parts and propose the Controllable fActor Feature Attribution (CAFA) approach to compute the relative importance of controllable features. We carried out experiments applying CAFA to two existing datasets and our own COVID-19 non-pharmaceutical control measures dataset. Experimental results show that with CAFA, we are able to exclude influences from uncontrollable features in our explanation while keeping the full dataset for prediction.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 12 of its 27 references that are in the map. First posted on arXiv 23 Mar 2022.
Builds on
12 of 27 references.
References · 12
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
- 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
- 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
- 2019Explainable AI for Trees: From Local Explanations to Global Understandingcited by 64
- 2020Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionatelycited by 52
- 2021Towards the Unification and Robustness of Perturbation and Gradient Based Explanationscited by 47
- 2021Evaluating the Correctness of Explainable AI Algorithms for Classificationcited by 8
- 2018Shedding Light on Black Box Machine Learning Algorithms: Development of an Axiomatic Framework to Assess the Quality of Methods that Explain Individual Predictionscited by 6
- 2021An Investigation of the Impact of COVID-19 Non-Pharmaceutical Interventions and Economic Support Policies on Foreign Exchange Markets with Explainable AI Techniquescited by 2
- 2020An Investigation of COVID-19 Spreading Factors with Explainable AI Techniquescited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.