Ahmed M. Abdelmoniem — accepted AI-conference papers

2025

Query-based Knowledge Transfer for Heterogeneous Learning Environments

Norah Alballa, Wenxuan Zhang, Ziquan Liu, Ahmed M. Abdelmoniem, Mohamed Elhoseiny, Marco Canini

ICLR 2025poster

Decentralized collaborative learning under data heterogeneity and privacy constraints has rapidly advanced. However, existing solutions like federated learning, ensembles, and transfer learning, often fail to adequately serve the unique needs of clients, especially when local data representation i…

Cited by 0 Source ↗PDF ↗Scholar ↗

2021

Rethinking gradient sparsification as total error minimization

Atal Narayan Sahu, Aritra Dutta, Ahmed M. Abdelmoniem, Trambak Banerjee, Marco Canini, Panos Kalnis

NeurIPS 2021spotlight

Gradient compression is a widely-established remedy to tackle the communication bottleneck in distributed training of large deep neural networks (DNNs). Under the error-feedback framework, Top-$k$ sparsification, sometimes with $k$ as little as 0.1% of the gradient size, enables training to the same…

Cited by 68 Source ↗PDF ↗Scholar ↗