24 citations · 29 across the 3 of their papers we have counts for
3 papers
AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation
Farshid Varno, Marzie Saghayi, Laya Rafiee Sevyeri +3
In Federated Learning (FL), a number of clients or devices collaborate to train a model without sharing their data. Models are optimized locally at each client and further communic…
Learn Faster and Forget Slower via Fast and Stable Task Adaptation
Farshid Varno, Lucas May Petry, Lisa Di Jorio +1
Training Deep Neural Networks (DNNs) is still highly time-consuming and compute-intensive. It has been shown that adapting a pretrained model may significantly accelerate this proc…
Efficient Neural Task Adaptation by Maximum Entropy Initialization
Farshid Varno, Behrouz Haji Soleimani, Marzie Saghayi +2
Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potential…