LUCID-GAN: Conditional Generative Models to Locate Unfairness
- URL: http://arxiv.org/abs/2307.15466v1
- Date: Fri, 28 Jul 2023 10:37:49 GMT
- Title: LUCID-GAN: Conditional Generative Models to Locate Unfairness
- Authors: Andres Algaba, Carmen Mazijn, Carina Prunkl, Jan Danckaert, Vincent
Ginis
- Abstract summary: We present LUCID-GAN, which generates canonical inputs via a conditional generative model instead of gradient-based inverse design.
We empirically evaluate LUCID-GAN on the UCI Adult and COMPAS data sets and show that it allows for detecting unethical biases in black-box models without requiring access to the training data.
- Score: 1.5257247496416746
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Most group fairness notions detect unethical biases by computing statistical
parity metrics on a model's output. However, this approach suffers from several
shortcomings, such as philosophical disagreement, mutual incompatibility, and
lack of interpretability. These shortcomings have spurred the research on
complementary bias detection methods that offer additional transparency into
the sources of discrimination and are agnostic towards an a priori decision on
the definition of fairness and choice of protected features. A recent proposal
in this direction is LUCID (Locating Unfairness through Canonical Inverse
Design), where canonical sets are generated by performing gradient descent on
the input space, revealing a model's desired input given a preferred output.
This information about the model's mechanisms, i.e., which feature values are
essential to obtain specific outputs, allows exposing potential unethical
biases in its internal logic. Here, we present LUCID-GAN, which generates
canonical inputs via a conditional generative model instead of gradient-based
inverse design. LUCID-GAN has several benefits, including that it applies to
non-differentiable models, ensures that canonical sets consist of realistic
inputs, and allows to assess proxy and intersectional discrimination. We
empirically evaluate LUCID-GAN on the UCI Adult and COMPAS data sets and show
that it allows for detecting unethical biases in black-box models without
requiring access to the training data.
Related papers
- Federated Causal Discovery from Heterogeneous Data [70.31070224690399]
We propose a novel FCD method attempting to accommodate arbitrary causal models and heterogeneous data.
These approaches involve constructing summary statistics as a proxy of the raw data to protect data privacy.
We conduct extensive experiments on synthetic and real datasets to show the efficacy of our method.
arXiv Detail & Related papers (2024-02-20T18:53:53Z) - Hierarchical Bias-Driven Stratification for Interpretable Causal Effect
Estimation [1.6874375111244329]
BICauseTree is an interpretable balancing method that identifies clusters where natural experiments occur locally.
We evaluate the method's performance using synthetic and realistic datasets, explore its bias-interpretability tradeoff, and show that it is comparable with existing approaches.
arXiv Detail & Related papers (2024-01-31T10:58:13Z) - LaPLACE: Probabilistic Local Model-Agnostic Causal Explanations [1.0370398945228227]
We introduce LaPLACE-explainer, designed to provide probabilistic cause-and-effect explanations for machine learning models.
The LaPLACE-Explainer component leverages the concept of a Markov blanket to establish statistical boundaries between relevant and non-relevant features.
Our approach offers causal explanations and outperforms LIME and SHAP in terms of local accuracy and consistency of explained features.
arXiv Detail & Related papers (2023-10-01T04:09:59Z) - Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy.
We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples.
Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
arXiv Detail & Related papers (2023-02-22T14:50:24Z) - LUCID: Exposing Algorithmic Bias through Inverse Design [1.5257247496416746]
We argue that output metrics encounter intrinsic obstacles and present a complementary approach that aligns with the increasing focus on equality of treatment.
We generate a canonical set that shows the desired inputs for a model given a preferred output.
We evaluate LUCID on the UCI Adult and COMPAS data sets and find that some biases detected by a canonical set differ from those of output metrics.
arXiv Detail & Related papers (2022-08-26T17:06:35Z) - Bounding Counterfactuals under Selection Bias [60.55840896782637]
We propose a first algorithm to address both identifiable and unidentifiable queries.
We prove that, in spite of the missingness induced by the selection bias, the likelihood of the available data is unimodal.
arXiv Detail & Related papers (2022-07-26T10:33:10Z) - Reusing the Task-specific Classifier as a Discriminator:
Discriminator-free Adversarial Domain Adaptation [55.27563366506407]
We introduce a discriminator-free adversarial learning network (DALN) for unsupervised domain adaptation (UDA)
DALN achieves explicit domain alignment and category distinguishment through a unified objective.
DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets.
arXiv Detail & Related papers (2022-04-08T04:40:18Z) - Error-based Knockoffs Inference for Controlled Feature Selection [49.99321384855201]
We propose an error-based knockoff inference method by integrating the knockoff features, the error-based feature importance statistics, and the stepdown procedure together.
The proposed inference procedure does not require specifying a regression model and can handle feature selection with theoretical guarantees.
arXiv Detail & Related papers (2022-03-09T01:55:59Z) - Interpretable Data-Based Explanations for Fairness Debugging [7.266116143672294]
Gopher is a system that produces compact, interpretable, and causal explanations for bias or unexpected model behavior.
We introduce the concept of causal responsibility that quantifies the extent to which intervening on training data by removing or updating subsets of it can resolve the bias.
Building on this concept, we develop an efficient approach for generating the top-k patterns that explain model bias.
arXiv Detail & Related papers (2021-12-17T20:10:00Z) - DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative
Networks [71.6879432974126]
We introduce DECAF: a GAN-based fair synthetic data generator for tabular data.
We show that DECAF successfully removes undesired bias and is capable of generating high-quality synthetic data.
We provide theoretical guarantees on the generator's convergence and the fairness of downstream models.
arXiv Detail & Related papers (2021-10-25T12:39:56Z) - Algorithmic Fairness Verification with Graphical Models [24.8005399877574]
We propose an efficient fairness verifier, called FVGM, that encodes correlations among features as a Bayesian network.
We show that FVGM leads to an accurate and scalable assessment for more diverse families of fairness-enhancing algorithms.
arXiv Detail & Related papers (2021-09-20T12:05:14Z)
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.