Model Explanations via the Axiomatic Causal Lens

• URL: http://arxiv.org/abs/2109.03890v7
• Date: Fri, 16 Feb 2024 00:16:03 GMT
• Title: Model Explanations via the Axiomatic Causal Lens
• Authors: Gagan Biradar, Vignesh Viswanathan, Yair Zick
• Abstract summary: We propose three explanation measures which aggregate the set of all but-for causes into feature importance weights. Our first measure is a natural adaptation of Chockler and Halpern's notion of causal responsibility. We extend our approach to derive a new method to compute the Shapley-Shubik and Banzhaf indices for black-box model explanations.
• Score: 9.915489218010952
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explaining the decisions of black-box models is a central theme in the study of trustworthy ML. Numerous measures have been proposed in the literature; however, none of them take an axiomatic approach to causal explainability. In this work, we propose three explanation measures which aggregate the set of all but-for causes -- a necessary and sufficient explanation -- into feature importance weights. Our first measure is a natural adaptation of Chockler and Halpern's notion of causal responsibility, whereas the other two correspond to existing game-theoretic influence measures. We present an axiomatic treatment for our proposed indices, showing that they can be uniquely characterized by a set of desirable properties. We also extend our approach to derive a new method to compute the Shapley-Shubik and Banzhaf indices for black-box model explanations. Finally, we analyze and compare the necessity and sufficiency of all our proposed explanation measures in practice using the Adult-Income dataset. Thus, our work is the first to formally bridge the gap between model explanations, game-theoretic influence, and causal analysis.

Related papers

• Counterfactual explainability of black-box prediction models [4.14360329494344]
  We propose a new notion called counterfactual explainability for black-box prediction models. Counterfactual explainability has three key advantages.
  arXiv  Detail & Related papers  (2024-11-03T16:29:09Z)
• Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance [72.50214227616728]
  Interpretability methods are valuable only if their explanations faithfully describe the explained model. We consider neural networks whose predictions are invariant under a specific symmetry group.
  arXiv  Detail & Related papers  (2023-04-13T17:59:03Z)
• Active Bayesian Causal Inference [72.70593653185078]
  We propose Active Bayesian Causal Inference (ABCI), a fully-Bayesian active learning framework for integrated causal discovery and reasoning. ABCI jointly infers a posterior over causal models and queries of interest. We show that our approach is more data-efficient than several baselines that only focus on learning the full causal graph.
  arXiv  Detail & Related papers  (2022-06-04T22:38:57Z)
• Explaining Causal Models with Argumentation: the Case of Bi-variate Reinforcement [15.947501347927687]
  We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models. The conceptualisation is based on reinterpreting desirable properties of semantics of AFs as explanation moulds. We perform a theoretical evaluation of these argumentative explanations, examining whether they satisfy a range of desirable explanatory and argumentative properties.
  arXiv  Detail & Related papers  (2022-05-23T19:39:51Z)
• Human Interpretation of Saliency-based Explanation Over Text [65.29015910991261]
  We study saliency-based explanations over textual data. We find that people often mis-interpret the explanations. We propose a method to adjust saliencies based on model estimates of over- and under-perception.
  arXiv  Detail & Related papers  (2022-01-27T15:20:32Z)
• Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
  Causal mechanisms can be described by structural causal models. One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
  arXiv  Detail & Related papers  (2021-09-06T14:52:58Z)
• On Shapley Credit Allocation for Interpretability [1.52292571922932]
  We emphasize the importance of asking the right question when interpreting the decisions of a learning model. This paper quantifies feature relevance by weaving different natures of interpretations together with different measures as characteristic functions for Shapley symmetrization.
  arXiv  Detail & Related papers  (2020-12-10T08:25:32Z)
• Towards Interpretable Reasoning over Paragraph Effects in Situation [126.65672196760345]
  We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect. We propose a sequential approach for this task which explicitly models each step of the reasoning process with neural network modules. In particular, five reasoning modules are designed and learned in an end-to-end manner, which leads to a more interpretable model.
  arXiv  Detail & Related papers  (2020-10-03T04:03:52Z)
• The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets [61.66584140190247]
  We show that feature-based explanations pose problems even for explaining trivial models. We show that two popular classes of explainers, Shapley explainers and minimal sufficient subsets explainers, target fundamentally different types of ground-truth explanations.
  arXiv  Detail & Related papers  (2020-09-23T09:45:23Z)
• Debiasing Concept-based Explanations with Causal Analysis [4.911435444514558]
  We study the problem of the concepts being correlated with confounding information in the features. We propose a new causal prior graph for modeling the impacts of unobserved variables. We show that our debiasing method works when the concepts are not complete.
  arXiv  Detail & Related papers  (2020-07-22T15:42:46Z)
• High Dimensional Model Explanations: an Axiomatic Approach [14.908684655206494]
  Complex black-box machine learning models are regularly used in critical decision-making domains. We propose a novel high dimension model explanation method that captures the joint effect of feature subsets.
  arXiv  Detail & Related papers  (2020-06-16T07:48:52Z)

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.