Towards a synergistic human-machine interaction and collaboration: XAI and Hybrid Decision Making Systems. State-of-the-art and research questions.
Sponsored by:
Abstract
Black box AI systems for automated decision-making, often based on machine learning over (big) data, map a user’s features into a class or a score without exposing the reasons why. This is problematic not only for the lack of transparency but also for possible biases inherited by the algorithms from human prejudices and collection artefacts hidden in the training data, which may lead to unfair or wrong decisions. The future of AI lies in enabling people to collaborate with machines to solve complex problems. Like any efficient collaboration, this requires good communication, trust, clarity and understanding. Explaining to humans how AI reasons are only a part of the problem means we must then be able to design AI systems that understand and collaborate with humans. Hybrid decision-making systems aim at leveraging the strengths of both human and machine agents to overcome the limitations that arise when either agent operates in isolation. This lecture provides a reasoned introduction to the work of Explainable AI (XAI) to date. Then, it will focus on paradigms supporting synergistic human-machine interaction and collaboration to improve joint performance in high-stake decision-making. Three distinct paradigms, characterized by a different degree of human agency, will be discussed: i) human oversight, with a human expert monitoring AI prediction augmented with explanation; ii) Learning to defer, in which the machine learning model is given the possibility to abstain from making a prediction when it receives an instance where the risk of making a misprediction is too large; iii) collaborative and interactive learning, in which human and AI engage in communication to integrate their distinct knowledge and facilitate the human’s ability to make informed decisions.
*This lecture is a joint work with Clara Punzi, Mattia Setzu and Roberto Pellungrini
Biography
Fosca Giannotti is professor of Computer Science at Scuola Normale Superiore, Pisa and associate at the Information Science and Technology Institute “A. Faedo” of CNR., Pisa, Italy. She co-leads the Pisa KDD Lab – Knowledge Discovery and Data Mining Laboratory, a joint research initiative of the University of Pisa and ISTI-CNR. Her research focuses on using AI and Big data to understand complex social phenomena: human mobility, social behaviour and advancing AI methods on trustworthiness and human interaction. She is the PI of the ERC project “XAI – Science and Technology for the Explanation of AI Decision Making”. She is the author of more than 300 papers. She has coordinated tens of European projects and industrial collaborations. Professor Giannotti is deputy director of SoBigData++, the European research infrastructure on Big Data Analytics and Social Mining, an ecosystem of tens of cutting-edge European research centres providing an open platform for interdisciplinary data science and data-driven innovation. On March 8, 2019, she was featured as one of the 19 Inspiring Women in AI, BigData, Data Science, and Machine Learning by KDnuggets.com, the leading site on AI, Data Mining and Machine Learning. html. Since February 2020, F.G. has been the Italian Delegate of Cluster 4 (Digital, Industry and Space) in Horizon Europe.