KIT | KIT-Bibliothek | Impressum | Datenschutz

Forming Effective Human-AI Teams: Building Machine Learning Models that Complement the Capabilities of Multiple Experts

Hemmer, Patrick 1,2; Schellhammer, Sebastian; Vössing, Michael ORCID iD icon 1,2; Jakubik, Johannes ORCID iD icon 1,2; Satzger, Gerhard 1,2
1 Karlsruhe Service Research Institute (KSRI), Karlsruher Institut für Technologie (KIT)
2 Institut für Wirtschaftsinformatik und Marketing (IISM), Karlsruher Institut für Technologie (KIT)

Abstract:

Machine learning (ML) models are increasingly being used in application domains that often involve working together with human experts. In this context, it can be advantageous to defer certain instances to a single human expert when they are difficult to predict for the ML model. While previous work has focused on scenarios with one distinct human expert, in many real-world situations several human experts with varying capabilities may be available. In this work, we propose an approach that trains a classification model to complement the capabilities of multiple human experts. By jointly training the classifier together with an allocation system, the classifier learns to accurately predict those instances that are difficult for the human experts, while the allocation system learns to pass each instance to the most suitable team member—either the classifier or one of the human experts. We evaluate our proposed approach in multiple experiments on public datasets with “synthetic” experts and a real-world medical dataset annotated by multiple radiologists. Our approach outperforms prior work and is more accurate than the best human expert or a classifier. ... mehr


Download
Originalveröffentlichung
DOI: 10.24963/ijcai.2022/344
Dimensions
Zitationen: 3
Zugehörige Institution(en) am KIT Institut für Wirtschaftsinformatik und Marketing (IISM)
Karlsruhe Service Research Institute (KSRI)
Publikationstyp Proceedingsbeitrag
Publikationsmonat/-jahr 07.2022
Sprache Englisch
Identifikator ISBN: 978-1-956792-00-3
KITopen-ID: 1000150990
Erschienen in Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Veranstaltung 31st International Joint Conference on Artificial Intelligence (IJCAI 2022), Wien, Österreich, 23.07.2022 – 29.07.2022
Verlag International Joint Conferences on Artificial Intelligence Organization (IJCAI)
Seiten 2478–2484
Externe Relationen Abstract/Volltext
Schlagwörter Human-AI Collaboration, Human-AI Teams, Human-AI Complementarity
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page