activity
20162025
most citedAn Efficient Statistical-based Gradient Compression Technique for Distributed Training Systems

31 citations · 74 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2025

Query-based Knowledge Transfer for Heterogeneous Learning Environments

Norah Alballa, Wenxuan Zhang, Ziquan Liu +3

Decentralized collaborative learning under data heterogeneity and privacy constraints has rapidly advanced. However, existing solutions like federated learning, ensembles, and tran…

cs.LG20241 cited

Flashback: Understanding and Mitigating Forgetting in Federated Learning

Mohammed Aljahdali, Ahmed M. Abdelmoniem, Marco Canini +1

In Federated Learning (FL), forgetting, or the loss of knowledge across rounds, hampers algorithm convergence, particularly in the presence of severe data heterogeneity among clien…

cs.LG2024

Practical Insights into Knowledge Distillation for Pre-Trained Models

Norah Alballa, Ahmed M. Abdelmoniem, Marco Canini

This research investigates the enhancement of knowledge distillation (KD) processes in pre-trained models, an emerging field in knowledge transfer with significant implications for…

cs.LG2023

Quantize Once, Train Fast: Allreduce-Compatible Compression with Provable Guarantees

Jihao Xin, Marco Canini, Peter Richtárik +1

Distributed training enables large-scale deep learning, but suffers from high communication overhead, especially as models and datasets grow. Gradient compression, particularly qua…

cs.LG202119 cited

Rethinking gradient sparsification as total error minimization

Atal Narayan Sahu, Aritra Dutta, Ahmed M. Abdelmoniem +3

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 fr…

cs.LG20215 cited

AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly

Yuchen Jin, Tianyi Zhou, Liangyu Zhao +4

The learning rate (LR) schedule is one of the most important hyper-parameters needing careful tuning in training DNNs. However, it is also one of the least automated parts of machi…