Artificial Intelligence (AI) and Machine Learning (ML) are transforming how today’s society, science, and business operate unprecedentedly, example including self-driving car, disease diagnosis, and AI stock trading. Huge data volume and variety greatly power up AI, and at the same time introduce new challenges arising from data poisoning and privacy concerns. In this talk, I will first discuss limitations of training ML models when encountering noisy stream data with privacy constraints, e.g., classification accuracy and utility loss. I will present a novel learning framework that combines human and artificial intelligence in distilling the detrimental impact of noisy data. Specific examples on classifying images with dirty labels will be given. I will conclude this talk by the challenges and potential solutions of generalizing and applying a plethora of trained models on applications, particularly for edge devices.

Lydia Y. Chen is an Associate Professor in the Department of Computer Science at the Delft University of Technology in The Netherlands. Prior to joining TU Delft, she was a research staff member at the IBM Research Zurich Lab from 2007 to 2018. She holds a PhD from Pennsylvania State University and a BA from National Taiwan University. Her research interests are distributed machine learning,  dependability management, resource allocation for large-scale data processing systems and services. More specifically, her work focuses on developing stochastic and machine learning models, and applying these techniques to application domains, such as data centers and AI systems. 

She has published more than 90 papers in peer-reviewed journals, including IEEE Transactions on Distributed Systems and IEEE Transactions on Service Computing, and in conference proceedings, including INFOCOM, SIGMETRICS, DSN, and EUROSYS. She was a co-recipient of the best paper awards at CCGrid’15 and eEnergy’15. She received TU Delft technology fellowship in 2018. She was program co-chair for IEEE ICAC 2019, Middleware Industry track 2018, track vice-chair for ICDCS 2018, and DIAS 2017. She has served on the editorial boards of IEEE Transactions on Service Computing and IEEE Transactions on Network and Service Management. She is a Senior Member of IEEE.