Reasoning for Complex Data through Self-Supervised Learning

***

Self-supervised learning deals with problems that have little or no available labeled data. Recent work has shown impressive results when underlying classes have significant semantic differences. We will discuss strategies to tackle to enable learning from unlabeled data even when samples from different classes are not prominently diverse. We approach the problem by leveraging novel ensemble-based clustering strategies where clusters derived from different configurations are combined to generate a better grouping for the data samples in a fully-unsupervised way. We will see results for Person Re-Identification and Text Authorship Verification but the techniques are useful in other applications as well. Moreover, we also detail recent efforts on Causal Analysis to refine AI methods.
Anderson Rocha (F) is a Full Professor of Artificial Intelligence and Digital Forensics at the Institute of Computing, University of Campinas (Unicamp), Brazil. He is the head of the Artificial Intelligence Lab., Recod.ai, at Unicamp and was the former Director of the Institute for the 2019-2023 term. He holds a bachelor's degree in Computer Science (2003) from Federal University of Lavras, Brazil, a Masters Degree in Computer Science (2006) from Unicamp and a Ph.D. degree in Computer Science (2009) also from Unicamp, Brazil.

Prof. Rocha is an elected affiliate of the Brazilian Academy of Sciences (ABC) and the Brazilian Academy of Forensic Sciences (ABC). He is a three-term elected member of the IEEE Information Forensics and Security Technical Committee (IFS-TC, 2011-2013, 2014-2016, 2023-2026) and a two-term former Chair of such committee (2015-2016, 2025-2026). He is a Microsoft Research (2011) and a Google (2017-2022) Research Faculty Fellow, an IEEE Fellow (2023), and IEEE Biometrics Distinguished Lecturer (2025-2027). In addition, in 2016, he was awarded the Tan Chin Tuan (TCT) Fellowship, and the Asia Pacific Artificial Intelligence Association Fellowship.

Prof. Rocha has been the principal investigator of several research projects in partnership with public funding agencies in Brazil and abroad and national and multi-national companies, having already filed and licensed several patents. He is a Brazilian CNPq research scholar (PQ1C). Finally, he is now a LinkedIn Top Voice in Artificial Intelligence for continuously raising awareness of Al and its potential impacts on society at large.