SANDS Lab
Home
News
Marco Canini
Contact
Teaching
Projects
Group
Publications
Open Positions
Ahmed M. Abdelmoniem Sayed
Alumni
Postdoc 2019, Research Scientist 2020-2021, now Associate Professor at QMUL
Latest
Flashback: Understanding and Mitigating Forgetting in Federated Learning
Analysis and Tuning of Knowledge Distillation for Efficient Collaborative Learning
Query-based Knowledge Transfer for Heterogeneous Learning Environments
A Comprehensive Empirical Study of Heterogeneity in Federated Learning
REFL: Resource-Efficient Federated Learning
Empirical Analysis of Federated Learning in Heterogeneous Environments
Rethinking gradient sparsification as total error minimization
GRACE: A Compressed Communication Framework for Distributed Machine Learning
DC2: Delay-aware Compression Control for Distributed Machine Learning
An Efficient Statistical-based Gradient Compression Technique for Distributed Training Systems
Towards Mitigating Device Heterogeneity in Federated Learning via Adaptive Model Quantization
SIDCo
Huffman Coding Based Encoding Techniques for Fast Distributed Deep Learning
On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning
DC2
Cite
×