activity
20172022
most citedStraggler-aware Distributed Learning: Communication Computation Latency Trade-off

48 citations · 50 across the 8 of their papers we have counts for

collaborators

19 papers

cs.IT20221 cited

Feedback is Good, Active Feedback is Better: Block Attention Active Feedback Codes

Emre Ozfatura, Yulin Shao, Amin Ghazanfari +3

Deep neural network (DNN)-assisted channel coding designs, such as low-complexity neural decoders for existing codes, or end-to-end neural-network-based auto-encoder designs are ga…

cs.LG2022

Semi-Decentralized Federated Learning with Collaborative Relaying

Michal Yemini, Rajarshi Saha, Emre Ozfatura +2

We present a semi-decentralized federated learning algorithm wherein clients collaborate by relaying their neighbors' local updates to a central parameter server (PS). At every com…

cs.LG2021

Less is More: Feature Selection for Adversarial Robustness with Compressive Counter-Adversarial Attacks

Emre Ozfatura, Muhammad Zaid Hameed, Kerem Ozfatura +1

A common observation regarding adversarial attacks is that they mostly give rise to false activation at the penultimate layer to fool the classifier. Assuming that these activation…

cs.IT2021

Gradient Coding with Dynamic Clustering for Straggler-Tolerant Distributed Learning

Baturalp Buyukates, Emre Ozfatura, Sennur Ulukus +1

Distributed implementations are crucial in speeding up large scale machine learning applications. Distributed gradient descent (GD) is widely employed to parallelize the learning t…

cs.LG2021

Time-Correlated Sparsification for Communication-Efficient Federated Learning

Emre Ozfatura, Kerem Ozfatura, Deniz Gunduz

Federated learning (FL) enables multiple clients to collaboratively train a shared model without disclosing their local datasets. This is achieved by exchanging local model updates…

cs.LG20201 cited

Distributed Sparse SGD with Majority Voting

Kerem Ozfatura, Emre Ozfatura, Deniz Gunduz

Distributed learning, particularly variants of distributed stochastic gradient descent (DSGD), are widely employed to speed up training by leveraging computational resources of sev…