Panagiotis A. Traganitis, Assistant Professor at Michigan State University, to speak at ECE-NTUA on December 12, 2022, at 13:00 (Conference hall B.0.10, ground floor, new ECE bulding)

Lecture Title: Learning from Unreliable Labels via Crowdsourcing

Abstract: Crowdsourcing has emerged as a powerful paradigm for tackling various machine learning, data mining, and data science tasks, by enlisting inexpensive crowds of human workers, or annotators, to accomplish learning and inference tasks. While conceptually related to distributed data and decision fusion, crowdsourcing seeks to not only aggregate information from multiple human annotators or unreliable (a.k.a. weak) sources, but to also assess their reliabilities. Crowdsourcing can thus be readily adapted to information fusion tasks in contested environments, where data may be provided from unreliable and even adversarial agents. Focusing on the classification task, exposition will include label aggregation, moments of annotator responses, dependencies of dynamic networked data, and robustness to adversaries demonstrated through extensive tests.

Short CV: Panagiotis A. Traganitis received his Diploma in Electrical and Computer Engineering from the National Technical University of Athens, Greece in 2013, his M.Sc. in Electrical Engineering in 2015 and his Ph.D. in Electrical Engineering in 2019, both from the University of Minnesota (UMN), Twin Cities. From 2019 to 2022, he was a postdoctoral researcher with the Department of Electrical and Computer Engineering (ECE) at the University of Minnesota, Twin Cities. In August 2022, he joined the ECE department at Michigan State University as an Assistant Professor. His research interests include statistical signal processing and learning, crowdsourcing and weak supervision, distributed learning, big data analytics, and network science.