Multi-Objective Counterfactuals for Counterfactual Fairness in User Centered AI
| dc.contributor.author | Amin, Rifat Mehreen | |
| dc.date.accessioned | 2023-08-24T06:24:30Z | |
| dc.date.available | 2023-08-24T06:24:30Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | This position paper emphasizes the role of user-centered artificial intelligence in critical decision-making domains in machine learning models. In this paper, I introduce MOCCF (Multi-Objective Counterfactuals for Counterfactual Fairness) as an extended method that generates realistic counterfactuals by leveraging multiple objectives. Furthermore, to increase transparency, I propose two fairness metrics, Absolute Mean Prediction Difference (AMPD), and Model Biasness Estimation (MBE). I argue that these metrics enable the detection and quantification of unfairness in binary classification models both at the individual and holistic levels consecutively and contribute to user-centered artificial intelligence. | en |
| dc.identifier.doi | 10.18420/muc2023-mci-ws16-397 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/42146 | |
| dc.publisher | GI | |
| dc.relation.ispartof | Mensch und Computer 2023 - Workshopband | |
| dc.relation.ispartofseries | Mensch und Computer | |
| dc.title | Multi-Objective Counterfactuals for Counterfactual Fairness in User Centered AI | en |
| dc.type | Text/Workshop Paper | |
| gi.conference.date | 3.-6. September 2023 | |
| gi.conference.location | Rapperswil | |
| gi.conference.sessiontitle | MCI-WS16 - UCAI 2023: Workshop on User-Centered Artificial Intelligence |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- muc23-mci-ws16-397.pdf
- Größe:
- 1.25 MB
- Format:
- Adobe Portable Document Format