paper-with-me

홈 › Papers

LUCID: Exposing Algorithmic Bias through Inverse Design

2022-08-26 · Carmen Mazijn, Carina Prunkl, Andres Algaba, Jan Danckaert, Vincent Ginis

AI systems can create, propagate, support, and automate bias in decision-making processes. To mitigate biased decisions, we both need to understand the origin of the bias and define what it means for an algorithm to make fair decisions. Most group fairness notions assess a model's equality of outcome by computing statistical metrics on the outputs. We argue that these output metrics encounter intrinsic obstacles and present a complementary approach that aligns with the increasing focus on equality of treatment. By Locating Unfairness through Canonical Inverse Design (LUCID), we generate a canonical set that shows the desired inputs for a model given a preferred output. The canonical set reveals the model's internal logic and exposes potential unethical biases by repeatedly interrogating the decision-making process. 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. The results show that by shifting the focus towards equality of treatment and looking into the algorithm's internal workings, the canonical sets are a valuable addition to the toolbox of algorithmic fairness evaluation.

📄 PDF Abstract BibTeX arXiv:2208.12786

Code (1)

integrated-intelligence-lab/canonical_sets pytorch

Tasks

Decision MakingFairness

Similar Papers 제목 키워드 기반

LUCID-GAN: Conditional Generative Models to Locate Unfairness

2023-07-28 · Andres Algaba, Carmen Mazijn, Carina Prunkl, Jan Danckaert 외

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 incomp…

Bias DetectionFairness

Whither Bias Goes, I Will Go: An Integrative, Systematic Review of Algorithmic Bias Mitigation

2024-10-21 · Louis Hickman, Christopher Huynh, Jessica Gass, Brandon Booth 외

Machine learning (ML) models are increasingly used for personnel assessment and selection (e.g., resume screeners, automatically scored interviews). However, concerns have been raised throughout society that ML assessmen…

Fairness

The Price equation reveals a universal force-metric-bias law of algorithmic learning and natural selection

2025-07-24 · Steven A. Frank arxiv

Diverse learning algorithms, optimization methods, and natural selection share a common mathematical structure, despite their apparent differences. Here I show that a simple notational partitioning of change by the Price…

An experiment on the mechanisms of racial bias in ML-based credit scoring in Brazil

2020-11-11 · Ramon Vilarino, Renato Vicente

We dissect an experimental credit scoring model developed with real data and demonstrate - without access to protected attributes - how the use of location information introduces racial bias. We analyze the tree gradient…

BIG-bench Machine Learningcounterfactual

NMR-Solver: Automated Structure Elucidation via Large-Scale Spectral Matching and Physics-Guided Fragment Optimization

2025-08-30 · Yongqi Jin, Jun-Jie Wang, Fanjie Xu, Xiaohong Ji 외 arxiv

Nuclear Magnetic Resonance (NMR) spectroscopy is one of the most powerful and widely used tools for molecular structure elucidation in organic chemistry. However, the interpretation of NMR spectra to determine unknown mo…