LUCID: Exposing Algorithmic Bias through Inverse Design
Open Access
- 26 June 2023
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (12) , 14391-14399
Abstract
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Interpretability and fairness evaluation of deep learning models on MIMIC-IV datasetScientific Reports, 2022
- Dreaming ideal protein structuresNature Biotechnology, 2022
- Inverse Design of Inflatable Soft Membranes Through Machine LearningAdvanced Functional Materials, 2022
- A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle2021
- Epistemic fragmentation poses a threat to the governance of online targetingNature Machine Intelligence, 2021
- Algorithmic bias: Senses, sources, solutionsPhilosophy Compass, 2021
- On the Applicability of Machine Learning Fairness NotionsACM SIGKDD Explorations Newsletter, 2021
- Artificial neural networks for inverse design of resonant nanophotonic components with oscillatory loss landscapesNanophotonics, 2020
- A snapshot of the frontiers of fairness in machine learningCommunications of the ACM, 2020
- Millions of black people affected by racial bias in health-care algorithmsNature, 2019