Name: Ahmed M. A. Sayed
Type: User
Company: Queen Mary University of London
Bio: aka. Ahmed M. Abdelmoniem - Assistant Professor at QMUL, UK - Head of SAYED Systems Group - Interested in ML, networking and Distributed Systems
Twitter: ahmedcs982
Location: London
Blog: www.eecs.qmul.ac.uk/~ahmed
Ahmed M. A. Sayed's Projects
P2P Distributed deep learning framework that runs on PyTorch.
TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"
SGD with compressed gradients and error-feedback: https://arxiv.org/abs/1901.09847
[KDD2021] Federated Adversarial Debiasing for Fair and Transferable Representations: Optimize an adversarial domain-adaptation objective without adversarial or source data.
Fair Resource Allocation in Federated Learning (ICLR '20)
Falken provides developers with a service that allows them to train AI that can play their games
An Industrial Grade Federated Learning Framework
Attentive Federated Learning for Private NLM
A framework for implementing federated learning
SRDS 2020: End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things
Implementation of Communication-Efficient Learning of Deep Networks from Decentralized Data
Multi-Stage Hybrid Federated Learning over Large-Scale Wireless Fog Networks
Salvaging Federated Learning by Local Adaptation
A multi-party collaborative machine learning framework
Code for Federated Learning with Matched Averaging, ICLR 2020.
FedMD: Heterogenous Federated Learning via Model Distillation
(PyTorch > 1.0) A Research-Oriented Federated Learning Library. Supporting distributed computing, mobile/IoT on-device training, and standalone simulation
Implementation of FedNova (NeurIPS 2020), and a class of federated learning algorithms, including FedAvg, FedProx.
Federated Optimization in Heterogeneous Networks (MLSys '20)
Federated learning with text DNNs for DATA 591 at University of Washington.
FlowBlaze: Stateful Packet Processing in Hardware
Benchmark for Federated Learning
Federation Learning Toolkit
Federated Multi-Task Learning
Deep learning with dynamic computation graphs in TensorFlow
code for TPDS paper "Towards Fair and Privacy-Preserving Federated Deep Models"