Presenter: Salvatore Greco
Wednesday, March 23rd, 2022 17:00
Despite the significant improvements made by deep learning models, their adoption in real-world dynamic applications is still limited. Concept drift is among the open issues preventing the widespread exploitation of deep learning models in real-life settings. The dynamic world changes very quickly, and the collected data drifts accordingly. Prediction models, usually trained on static historical data, should be promptly re-trained in case of new real-time drifted data distributions.
In this SmartTalk, we present a novel real-time unsupervised per-label drift detection methodology based on embedding distribution distances in deep learning models.
The preliminary experiments performed on a transformer-based model (BERT) fine-tuned for topic text classification show promising results in drift detection accuracy, drift characterization, and efficient execution time to support real-time concept drift detection.
Biography: Salvatore Greco is a second-year PhD student at Department of Control and Computer Engineering (DAUIN), Politecnico di Torino and member of the SmartData@Polito center. His main research interests are focused on eXplainable Artificial Intelligence (XAI) and Natural Language Processing (NLP).