Dino Pedreschi

Data and Algorithmic Bias: Explaining the Network Effect in Opinion Dynamics and the Training Data Bias in Machine Learning

Presenter: Dino Pedreschi, KDD Laboratory, Dipartimento di Informatica, Universita di Pisa, (DI-UNIPI) and Istituto di Scienza e Tecnologie dell’Informazione, Consiglio Nazionale delle Ricerche (ISTI-CNR),Pisa, Italy (pedre@di.unipi.it)


Data science and network science are creating novel means to study the complexity of our societies and to measure, understand and predict social phenomena. My talk gives an overview of recent research at the Knowledge Discovery (KDD) Lab in Pisa within the SoBigData.eu research infrastructure, targeted at explaining the effects of data and algorithmic bias in different domains, using both data-driven and model-driven arguments. First, I introduce a model showing how algorithmic bias instilled in an opinion diffusion process artificially yields increased polarisation, fragmentation and instability in a population. Second, I focus on the urgent open challenge of how to construct meaningful explanations of opaque AI/ML black-box decision systems, introducing the local-to-global framework for the explanation of ML classifiers as a way towards explainable AI. The two cases show how the combination of data-driven and model-driven interdisciplinary research has a huge potential to shed new light on complex phenomena like discrimination and polarisation, as well as to explain how decision making black-boxes, both human and artificial, actually work. I conclude with an account of the open data science paradigm pursued in SoBigData.eu Research Infrastructure and its importance for interdisciplinary data driven science that impacts societal challenges.

Short-bio of presenter

Dino Pedreschi is a professor of computer science at the University of Pisa, and a pioneering scientist in data science. He co-leads the Pisa KDD Lab – Knowledge Discovery and Data Mining Laboratory, a joint research initiative of the University of Pisa and the Information Science and Technology Institute of the Italian National Research Council. His research focus is on big data analytics and mining and their impact on society. He is a founder of the Business Informatics MSc program at University of Pisa, a course targeted at the education of interdisciplinary data scientists, and of SoBigData.eu, the European H2020 Research Infrastructure Big Data Analytics and Social Mining Ecosystem. Dino has been a visiting scientist at Barabasi Lab (Center for Complex Network Research) of Northeastern University, Boston, and earlier at the University of Texas at Austin, at CWI Amsterdam and at UCLA. In 2009, Dino received a Google Research Award for his research on privacy-preserving data mining. Dino is a member of the expert group in AI of the Italian Ministry of research and the director of the Data Science PhD program at Scuola Normale Superiore in Pisa. Dino is a co-PI of the 2019 ERC grant XAI – Science and technology for the explanation of AI decision making (PI: Fosca Giannotti).

Important Dates

  • Paper submission (Extended): 25.6.2019
  • Author notification (Extended): 29.7.2019
  • PhD session abstract submission (Extended): 1.9.2019
  • PhD abstract notification (Extended): 4.9.2019
  • Camera ready (Extended): 20.8.2019
  • Author registration (For authors of accepted papers): 20.8.2019
  • Late Breaking Contributions: 8.9.2019
  • PhD Symposium registration (Extended): 8.9.2019
  • Early (non-author) registration (Extended): 16.9.2019
  • Regular registration: 27.10.2019
  • Conference: 28. - 30.10.2019

This site uses cookies.

Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and can only be disabled by changing your browser preferences.