Multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainers

• URL: http://arxiv.org/abs/2403.13940v1
• Date: Wed, 20 Mar 2024 19:25:11 GMT
• Title: Multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainers
• Authors: Ignacy Stępka, Mateusz Lango, Jerzy Stefanowski,
• Abstract summary: We propose to use a multi-stage ensemble approach that will select single counterfactual based on the multiple-criteria analysis. The proposed approach generates fully actionable counterfactuals with attractive compromise values of the considered quality measures.
• Score: 4.239829789304117
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Counterfactuals are widely used to explain ML model predictions by providing alternative scenarios for obtaining the more desired predictions. They can be generated by a variety of methods that optimize different, sometimes conflicting, quality measures and produce quite different solutions. However, choosing the most appropriate explanation method and one of the generated counterfactuals is not an easy task. Instead of forcing the user to test many different explanation methods and analysing conflicting solutions, in this paper, we propose to use a multi-stage ensemble approach that will select single counterfactual based on the multiple-criteria analysis. It offers a compromise solution that scores well on several popular quality measures. This approach exploits the dominance relation and the ideal point decision aid method, which selects one counterfactual from the Pareto front. The conducted experiments demonstrated that the proposed approach generates fully actionable counterfactuals with attractive compromise values of the considered quality measures.

Related papers

• An Efficient Approach for Solving Expensive Constrained Multiobjective Optimization Problems [0.0]
  An efficient probabilistic selection based constrained multi-objective EA is proposed, referred to as PSCMOEA. It comprises novel elements such as (a) an adaptive search bound identification scheme based on the feasibility and convergence status of evaluated solutions. Numerical experiments are conducted on an extensive range of challenging constrained problems using low evaluation budgets to simulate ECMOPs.
  arXiv  Detail & Related papers  (2024-05-22T02:32:58Z)
• UCB-driven Utility Function Search for Multi-objective Reinforcement Learning [75.11267478778295]
  In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours. We focus on the case of linear utility functions parameterised by weight vectors w. We introduce a method based on Upper Confidence Bound to efficiently search for the most promising weight vectors during different stages of the learning process.
  arXiv  Detail & Related papers  (2024-05-01T09:34:42Z)
• Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis [52.04932081106623]
  We propose a unified framework to interpret and evaluate the existing probability-based prompt selection methods. We find that each of the existing methods can be interpreted as some variant of the method that maximizes mutual information between the input and the predicted output (MI) We propose a novel calibration method called by Marginalization (CBM) that is to the existing methods and helps increase the prompt selection effectiveness of the best method to 96.85%, achieving 99.44% of the oracle prompt F1 without calibration.
  arXiv  Detail & Related papers  (2023-05-24T08:29:50Z)
• Better Understanding Differences in Attribution Methods via Systematic Evaluations [57.35035463793008]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models.
  arXiv  Detail & Related papers  (2023-03-21T14:24:58Z)
• Bi-objective Ranking and Selection Using Stochastic Kriging [0.0]
  We consider bi-objective ranking and selection problems in which the two objective outcomes have been observed with uncertainty. We propose a novel Bayesian bi-objective ranking and selection method that sequentially allocates extra samples to competitive solutions. Experimental results show that the proposed method outperforms the standard allocation method, as well as a well-known state-of-the-art algorithm.
  arXiv  Detail & Related papers  (2022-09-05T23:51:07Z)
• Selection of a representative sorting model in a preference disaggregation setting: a review of existing procedures, new proposals, and experimental comparison [4.447467536572626]
  We consider preference disaggregation in the context of multiple criteria sorting. Given the multiplicity of sorting models compatible with indirect preferences, selecting a single, representative one can be conducted differently. We present three novel procedures that implement the robust assignment rule in practice.
  arXiv  Detail & Related papers  (2022-08-30T02:01:35Z)
• Learning Proximal Operators to Discover Multiple Optima [66.98045013486794]
  We present an end-to-end method to learn the proximal operator across non-family problems. We show that for weakly-ized objectives and under mild conditions, the method converges globally.
  arXiv  Detail & Related papers  (2022-01-28T05:53:28Z)
• Robust, Accurate Stochastic Optimization for Variational Inference [68.83746081733464]
  We show that common optimization methods lead to poor variational approximations if the problem is moderately large. Motivated by these findings, we develop a more robust and accurate optimization framework by viewing the underlying algorithm as producing a Markov chain.
  arXiv  Detail & Related papers  (2020-09-01T19:12:11Z)
• Bayesian preference elicitation for multiobjective combinatorial optimization [12.96855751244076]
  We introduce a new incremental preference elicitation procedure able to deal with noisy responses of a Decision Maker (DM) We assume that the preferences of the DM are represented by an aggregation function whose parameters are unknown and that the uncertainty about them is represented by a density function on the parameter space.
  arXiv  Detail & Related papers  (2020-07-29T12:28:37Z)
• Learning the Truth From Only One Side of the Story [58.65439277460011]
  We focus on generalized linear models and show that without adjusting for this sampling bias, the model may converge suboptimally or even fail to converge to the optimal solution. We propose an adaptive approach that comes with theoretical guarantees and show that it outperforms several existing methods empirically.
  arXiv  Detail & Related papers  (2020-06-08T18:20:28Z)
• Multi-Objective Counterfactual Explanations [0.7349727826230864]
  We propose the Multi-Objective Counterfactuals (MOC) method, which translates the counterfactual search into a multi-objective optimization problem. Our approach not only returns a diverse set of counterfactuals with different trade-offs between the proposed objectives, but also maintains diversity in feature space.
  arXiv  Detail & Related papers  (2020-04-23T13:56:39Z)

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.