Phone (office): +39 049 827 7774
BIOGRAPHY
Donald Shenaj is a PhD Student at the Department of Information Engineering of the University of Padova. He received the Bachelor’s Degree in Electronics Engineering at University of Bologna in October 2019, and the Master’s Degree in ICT for Internet and Multimedia at University of Padova in September 2021, both with honors. Currently, he is a visiting researcher at Mila – Quebec Artificial Intelligence Institute in Montreal, Canada. He is interested in large scale machine learning problems and their applications to computer vision.
Website: https://donaldssh.github.io/
Research areas
Federated Learning
Federated learning is a decentralized machine learning approach that allows multiple devices to train a shared model collaboratively while keeping their local data private.
Continual Learning
Continual learning refers to the ability of a machine learning model to continuously acquire and retain knowledge from new data while retaining previously learned information.
Domain Adaptation
Domain Adaptation aligns a network from a source dataset to perform on a target dataset with a different distribution. Complex neural networks require abundant labeled data, which limits their application in many real-world scenarios.
Publications
2023
Asynchronous Federated Continual Learning Proceedings Article
In: CVPR FedVision Workshop, 2023.
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning Proceedings Article
In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023, 2023.
Federated Learning in Computer Vision Journal Article
In: IEEE Access, 2023.
2022
Continual coarse-to-fine domain adaptation in semantic segmentation Journal Article
In: Image and Vision Computing, vol. 121, pp. 104426, 2022.