Li Ju
About me
I am a third-year Ph.D candidate in Scientific Computing at Uppsala University, supervised by Associate Professor Andreas Hellander. Prior to starting my Ph.D study, I earned MS.c in Computational Science at Uppsala University, MS.c in Chemometrics at University of Science and Technology of China (USTC), and BS.c in Chemistry at USTC.
Research Interests
I am currently working on both theoretical and applied federated machine learning. I am in paticular interested in the data heterogeneity problems in federated learning.
News
- 11/24: Our team secured 2nd place at Huawei Sweden Hackathon 2024, tackling wireless localisation problems using machine learning methods.
- 10/24: I had a poster presentation at the Swedish e-Science Academy about the theoretical analysis for the application of logit adjustment in heterogeneous federated learning.
- 06/24: Our paper “Accelerating Fair Federated Learning: Adaptive Federated Adam” got accepted in IEEE Transactions on Machine Learning in Communications and Networking.
- 04/24: Our paper “Federated Learning for Predicting Compound Mechanism of Action Based on Image-data from Cell Painting” got accepted in Artificial Intelligence in the Life Sciences.
- 01/24: Our paper “Blades: A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning” got accepted in IoTDI ‘24.
- 10/22: I had a poster presentation at the Swedish e-Science Academy about accelerating fair federated learning in Umeå, Sweden.
- 06/22: We released Blades, a simulator for Byzantine-robust federated learning with attacks and defenses.
- 12/21: Our paper “Proactive autoscaling for edge computing systems with kubernetes” got accepted in UCC ‘21.
- 09/21: I started my Ph.D study at TDB, Uppsala University, co-supervised by Andreas Hellander and Salman Toor.