Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps

• URL: http://arxiv.org/abs/2305.09399v2
• Date: Wed, 17 May 2023 07:30:40 GMT
• Title: Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps
• Authors: Isel Grau, Gonzalo N\'apoles, Fabian Hoitsma, Lisa Koutsoviti Koumeri, Koen Vanhoof
• Abstract summary: In this paper, we integrate the concepts of feature importance with implicit bias in the context of pattern classification. The amount of bias towards protected features might differ depending on whether the features are numerically or categorically encoded.
• Score: 1.9739269019020032
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we integrate the concepts of feature importance with implicit bias in the context of pattern classification. This is done by means of a three-step methodology that involves (i) building a classifier and tuning its hyperparameters, (ii) building a Fuzzy Cognitive Map model able to quantify implicit bias, and (iii) using the SHAP feature importance to active the neural concepts when performing simulations. The results using a real case study concerning fairness research support our two-fold hypothesis. On the one hand, it is illustrated the risks of using a feature importance method as an absolute tool to measure implicit bias. On the other hand, it is concluded that the amount of bias towards protected features might differ depending on whether the features are numerically or categorically encoded.

Related papers

• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision [51.176061115977774]
  We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP) We then systematically evaluate existing methods for mitigating bias in these models with respect to our taxonomy. Specifically, we evaluate OpenAI's CLIP and OpenCLIP models for key applications, such as zero-shot classification, image retrieval and image captioning.
  arXiv  Detail & Related papers  (2023-10-18T10:32:39Z)
• Generalizing Backpropagation for Gradient-Based Interpretability [103.2998254573497]
  We show that the gradient of a model is a special case of a more general formulation using semirings. This observation allows us to generalize the backpropagation algorithm to efficiently compute other interpretable statistics.
  arXiv  Detail & Related papers  (2023-07-06T15:19:53Z)
• On the Joint Interaction of Models, Data, and Features [82.60073661644435]
  We introduce a new tool, the interaction tensor, for empirically analyzing the interaction between data and model through features. Based on these observations, we propose a conceptual framework for feature learning. Under this framework, the expected accuracy for a single hypothesis and agreement for a pair of hypotheses can both be derived in closed-form.
  arXiv  Detail & Related papers  (2023-06-07T21:35:26Z)
• FACT: High-Dimensional Random Forests Inference [4.941630596191806]
  Quantifying the usefulness of individual features in random forests learning can greatly enhance its interpretability. Existing studies have shown that some popularly used feature importance measures for random forests suffer from the bias issue. We propose a framework of the self-normalized feature-residual correlation test (FACT) for evaluating the significance of a given feature.
  arXiv  Detail & Related papers  (2022-07-04T19:05:08Z)
• Discriminative Attribution from Counterfactuals [64.94009515033984]
  We present a method for neural network interpretability by combining feature attribution with counterfactual explanations. We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
  arXiv  Detail & Related papers  (2021-09-28T00:53:34Z)
• Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization [77.8735802150511]
  We propose a cross-sample adversarial debiasing (CSAD) method to remove the bias information misused by the target task. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-08-11T21:17:02Z)
• Path Integrals for the Attribution of Model Uncertainties [0.18899300124593643]
  We present a novel algorithm that relies on in-distribution curves connecting a feature vector to some counterfactual counterpart. We validate our approach on benchmark image data sets with varying resolution, and show that it significantly simplifies interpretability.
  arXiv  Detail & Related papers  (2021-07-19T11:07:34Z)
• Do Input Gradients Highlight Discriminative Features? [42.47346844105727]
  Interpretability methods seek to explain instance-specific model predictions. We introduce an evaluation framework to study this hypothesis for benchmark image classification tasks. We make two surprising observations on CIFAR-10 and Imagenet-10 datasets.
  arXiv  Detail & Related papers  (2021-02-25T11:04:38Z)
• Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
  Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
  arXiv  Detail & Related papers  (2021-02-12T12:23:13Z)
• Achieving Equalized Odds by Resampling Sensitive Attributes [13.114114427206678]
  We present a flexible framework for learning predictive models that approximately satisfy the equalized odds notion of fairness. This differentiable functional is used as a penalty driving the model parameters towards equalized odds. We develop a formal hypothesis test to detect whether a prediction rule violates this property, the first such test in the literature.
  arXiv  Detail & Related papers  (2020-06-08T00:18:34Z)

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.