We are gradually moving towards an era in which many decision making policies are supported by Artificial Intelligence (AI) systems. Technologies that apply AI algorithms or utilize AI systems have shown a great proliferation and have significant impact in a lot of aspects of the citizens' everyday life as well as in the industry. The utilization of AI systems in numerous industrial and public service domains is becoming increasingly prevalent in our daily lives. In the contemporary era, Artificial Intelligence drives various systems like recommending content on social media, enabling machine vision in self-driving cars, and determining whether to approve or deny loans for bank clients. These examples vividly illustrate the essential influence of AI algorithms and their potential to shape our lives, significantly impacting the decision-making process. Hence, their effective operation holds vital importance for both individuals and society in its entirety. This workshop aims at discussing such fairness challenges and issues in AI systems and how to address them.
| Time (CEST) - 13/5/2024 | Title | Speaker/Authors |
| 08:30 - 08:45 | Conference Registration | |
| 08:45 - 09:00 | Opening | |
| 09:00 - 10:00 | Keynote talk I: Explainable, actionable, and fair machine learning and its implications to healthcare Abstract: In this talk, I will introduce some key concepts of explainability in relation to machine learning models. Examples of local and global explainers will be provided in the context of healthcare applications. Moreover, I will discuss the need for counterfactual explanations, and how these relate to causality. Some recent counterfactual explainers will be presented with emphasis on time series data sources. To further elaborate on the implications of machine learning in healthcare, we will explore the practical challenges and ethical considerations associated with deploying these models. This includes addressing issues of fairness and bias, which are crucial for ensuring that healthcare interventions are equitable across different patient demographics. Additionally, I will highlight the importance of actionable insights derived from machine learning models, illustrating how they can lead to improved patient outcomes and more efficient healthcare services. We will also examine case studies where explainable AI has been successfully integrated into clinical settings, showcasing the tangible benefits and potential hurdles of such implementations. This discussion aims to provide a comprehensive overview of the current landscape and future directions in the use of explainable, actionable, and fair machine learning in healthcare. |
Panagiotis Papapetrou (Stockholm University, Sweden, Faculty of Social Sciences, Department of Computer and Systems Sciences) Bio: Panagiotis Papapetrou is a Professor at the Department of Computer and Systems Sciences at Stockholm University and Adjunct Professor at the Computer Science Department at Aalto University. His area of expertise is algorithmic data mining with particular focus on time series mining and indexing temporal data, with emphasis on healthcare. Panagiotis received his PhD in Computer Science at Boston University in 2009, was a post-doctoral researcher at Aalto University during 2009-2013, and lecturer at the University of London during 2012-2013. He has participated in several national and international research projects. He is action editor of DAMI and board member of the Swedish AI Society. He has held tutorials on topics in data mining and healthcare at ECML/PKDD 2016, ICDM 2017, and KDD 2018. |
| 10:00 - 10:20 | Coffee Break | |
| 10:20 - 10:40 | Closed-Loop View of the Regulation of AI: Equal Impact across Repeated Interactions | Quan Zhou (Imperial College London), Ramen Ghosh (Atlantic Technological University), Robert Shorten (Imperial College London), Jakub Mareček (Czech Technical University in Prague) |
| 10:40 - 11:00 | Examing and Explaining Individual Fairness in Dynamic Pricing | Wei Guo (School of Computer Science and Engineering Southeast University Nanjin, China), Yan Lyu (School of Computer Science and Engineering Southeast University Nanjin, China), Weiwei Wu (School of Computer Science and Engineering Southeast University Nanjin, China) |
| 11:00 - 11:20 | Inspecting and Measuring Fairness of unlabeled Image Datasets | Rebekka Görge (Fraunhofer IAIS), Michael Mock (Fraunhofer IAIS), Maram Akila (Fraunhofer IAIS & Lamarr) |
| 11:20 - 11:40 | Fairness in Ranking: Robustness through Randomization without the Protected Attribute | Andrii Kliachkin (Department of Mathematics, Universit`a degli Studi di Padova), Eleni Psaroudaki (National Technical University of Athens, Athena Research & Innovation Center in Information Communication & Knowledge Technologies), Jakub Mareček (Czech Technical University in Prague), Dimitris Fotakis (National Technical University of Athens, Athena Research & Innovation Center in Information Communication & Knowledge Technologies) |
| 11:40 - 12:00 | Pricefair: On fair scheduling of heterogeneous resources | Aristotelis Peri (Athens University of Economics and Business), Dimitrios Tomaras (Athens University of Economics and Business), Vana Kalogeraki (Athens University of Economics and Business), Dimitrios Gunopulos (National and Kapodistrian University of Athens) |
| 12:00 - 13:30 | Lunch Break | |
| 13:30 - 13:50 | Fairness in AI: bridging the gap between algorithms and law | Giorgos Giannopoulos (Athena Research Center), Maria Psalla (Athena Research Center), Loukas Kavouras (Athena Research Center), Dimitris Sacharidis (Universite Libre Brussels), Jakub Mareček (Czech Technical University), German Martinez (Czech Technical University), Ioannis Emiris (Athena Research Center) |
| 13:50 - 14:10 | Optimal Transport for Fairness: Archival Data Repair using Small Research Data Sets | Abigail Langbridge (Dyson School of Design Engineering, Imperial College London), Anthony Quinn (Dyson School of Design Engineering, Imperial College London / Department of Electronic and Electrical Engineering, Trinity College Dublin), Robert Shorten (Dyson School of Design Engineering, Imperial College London) |
| 14:10 - 14:30 | A Framework for Feasible Counterfactual Exploration incorporating Causality, Sparsity and Density | Kleopatra Markou (National and Kapodistrian University of Athens), Dimitrios Tomaras (Athens University of Economics and Business), Vana Kalogeraki (Athens University of Economics and Business), Dimitrios Gunopulos (National and Kapodistrian University of Athens) |
| 15:00 - 15:30 | Coffee Break | |
| 15:30 - 15:50 | Exploring Fairness Interpretability with FairnessFriend: A Chatbot Solution | Chiara Criscuolo (DEIB – Politecnico di Milano), Tommaso Dolci (DEIB – Politecnico di Milano) |
| 15:50 - 16:10 | On Explaining Unfairness: An Overview | Christos Fragkathoulas (University of Ioannina, Archimedes / Athena RC), Vasiliki Papanikou (University of Ioannina, Archimedes / Athena RC), Danae Pla Karidi (Archimedes / Athena RC), Evaggelia Pitoura (University of Ioannina, Archimedes / Athena RC) |
| 16:50 - 17:20 | Panel Discussion | |
| 17:20 - 17:30 | Closing | |
We encourage submissions in various degrees of progress, such as new results, visions, techniques and innovative application papers. We particularly encourage interdisciplinary work that lies on the topics that include, but are not limited to, the following broad categories:
The workshop will accept regular papers and adopts a single-blind review process.
The FAIR workshop will take place in Theater 4 in Kinepolis Jaarbeurs theater.
The 1st International Workshop on Fairness in AI is co-located with ICDE. This year ICDE will take place in Utrecht. It is the fourth largest city in the Netherlands, located right in the middle of the country, and is a major transportation hub. The historical part of the city features many buildings dating back in the middle ages. It has been the religious centre of the Netherlands since the 8th century and the most important city. It had been the country's cultural centre, until the 16th century when it was surpassed by Amsterdam. Today, it hosts the second-highest number of cultural events in the country. It is home to Utrecht University, the largest university in the Netherlands, that is ranked internationally in the 66th position by the Times Higher Education University Rankings.