Speaker
Xiaoxiao Li
(Electrical and Computer Engineering, The University of British Columbia)
Description
The challenges posed by small and heterogeneous medical datasets significantly impede AI development in biomedical data analysis. My research addresses this issue by utilizing innovative partially personalized federated learning frameworks. These frameworks facilitate collaborative learning across multiple medical centers, enhancing the development of precise, personalized AI models. In this presentation, I will begin by introducing the concept of federated learning. Following this, I will present two straightforward yet effective methods for enabling personalized federated learning to support biomedical data analysis using convolutional neural networks and transformers.
| Keyword-1 | Deep learning |
|---|---|
| Keyword-2 | Biomedical data analysis |
| Keyword-3 | Trustworthiness of AI systems |
Primary author
Xiaoxiao Li
(Electrical and Computer Engineering, The University of British Columbia)
