48 citations · 86 across the 24 of their papers we have counts for
34 papers
TransCoder: A Neural-Enhancement Framework for Channel Codes
Anastasiia Kurmukova, Selim F. Yilmaz, Emre Ozfatura +1
Reliable communication over noisy channels requires the design of specialized error-correcting codes (ECCs) tailored to specific system requirements. Recently, neural network-based…
Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning
Emre Ozfatura, Kerem Ozfatura, Baturalp Buyukates +3
In federated learning (FL), profiling and verifying each client is inherently difficult, which introduces a significant security vulnerability: malicious clients, commonly referred…
Process-and-Forward: Deep Joint Source-Channel Coding Over Cooperative Relay Networks
Chenghong Bian, Yulin Shao, Haotian Wu +2
We introduce deep joint source-channel coding (DeepJSCC) schemes for image transmission over cooperative relay channels. The relay either amplifies-and-forwards its received signal…
Transformer-aided Wireless Image Transmission with Channel Feedback
Haotian Wu, Yulin Shao, Emre Ozfatura +2
This paper presents a novel wireless image transmission paradigm that can exploit feedback from the receiver, called DeepJSCC-ViT-f. We consider a block feedback channel model, whe…
Do not Interfere but Cooperate: A Fully Learnable Code Design for Multi-Access Channels with Feedback
Emre Ozfatura, Chenghong Bian, Deniz Gunduz
Data-driven deep learning based code designs, including low-complexity neural decoders for existing codes, or end-to-end trainable auto-encoders have exhibited impressive results,…
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…
Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning
Kerem Ozfatura, Emre Ozfatura, Alptekin Kupcu +1
The increasing popularity of the federated learning (FL) framework due to its success in a wide range of collaborative learning tasks also induces certain security concerns. Among…
All you need is feedback: Communication with block attention feedback codes
Emre Ozfatura, Yulin Shao, Alberto Perotti +2
Deep learning based channel code designs have recently gained interest as an alternative to conventional coding algorithms, particularly for channels for which existing codes do no…
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…
AttentionCode: Ultra-Reliable Feedback Codes for Short-Packet Communications
Yulin Shao, Emre Ozfatura, Alberto Perotti +2
Ultra-reliable short-packet communication is a major challenge in future wireless networks with critical applications. To achieve ultra-reliable communications beyond 99.999%, this…
Federated Spatial Reuse Optimization in Next-Generation Decentralized IEEE 802.11 WLANs
Francesc Wilhelmi, Jernej Hribar, Selim F. Yilmaz +10
As wireless standards evolve, more complex functionalities are introduced to address the increasing requirements in terms of throughput, latency, security, and efficiency. To unlea…
Robust Federated Learning with Connectivity Failures: A Semi-Decentralized Framework with Collaborative Relaying
Michal Yemini, Rajarshi Saha, Emre Ozfatura +2
Intermittent connectivity of clients to the parameter server (PS) is a major bottleneck in federated edge learning frameworks. The lack of constant connectivity induces a large gen…
Collaborative Learning over Wireless Networks: An Introductory Overview
Emre Ozfatura, Deniz Gunduz, H. Vincent Poor
In this chapter, we will mainly focus on collaborative training across wireless devices. Training a ML model is equivalent to solving an optimization problem, and many distributed…
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…
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…
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…
FedADC: Accelerated Federated Learning with Drift Control
Kerem Ozfatura, Emre Ozfatura, Deniz Gunduz
Federated learning (FL) has become de facto framework for collaborative learning among edge devices with privacy concern. The core of the FL strategy is the use of stochastic gradi…
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…
Gradient Coding with Dynamic Clustering for Straggler Mitigation
Baturalp Buyukates, Emre Ozfatura, Sennur Ulukus +1
In distributed synchronous gradient descent (GD) the main performance bottleneck for the per-iteration completion time is the slowest \textit{straggling} workers. To speed up GD it…
Communicate to Learn at the Edge
Deniz Gunduz, David Burth Kurka, Mikolaj Jankowski +3
Bringing the success of modern machine learning (ML) techniques to mobile devices can enable many new services and businesses, but also poses significant technical and research cha…
Coded Distributed Computing with Partial Recovery
Emre Ozfatura, Sennur Ulukus, Deniz Gunduz
Coded computation techniques provide robustness against straggling workers in distributed computing. However, most of the existing schemes require exact provisioning of the straggl…
Age-Based Coded Computation for Bias Reduction in Distributed Learning
Emre Ozfatura, Baturalp Buyukates, Deniz Gunduz +1
Coded computation can be used to speed up distributed learning in the presence of straggling workers. Partial recovery of the gradient vector can further reduce the computation tim…
Straggler-aware Distributed Learning: Communication Computation Latency Trade-off
Emre Ozfatura, Sennur Ulukus, Deniz Gunduz
When gradient descent (GD) is scaled to many parallel workers for large scale machine learning problems, its per-iteration computation time is limited by the straggling workers. St…
Decentralized SGD with Over-the-Air Computation
Emre Ozfatura, Stefano Rini, Deniz Gunduz
We study the performance of decentralized stochastic gradient descent (DSGD) in a wireless network, where the nodes collaboratively optimize an objective function using their local…