Search Results for author: Deniz Gündüz

Found 17 papers, 4 papers with code

DeepWiVe: Deep-Learning-Aided Wireless Video Transmission

no code implementations25 Nov 2021 Tze-Yang Tung, Deniz Gündüz

We present DeepWiVe, the first-ever end-to-end joint source-channel coding (JSCC) video transmission scheme that leverages the power of deep neural networks (DNNs) to directly map video signals to channel symbols, combining video compression, channel coding, and modulation steps into a single neural transform.

MS-SSIM SSIM +1

DeepJSCC-Q: Channel Input Constrained Deep Joint Source-Channel Coding

no code implementations25 Nov 2021 Tze-Yang Tung, David Burth Kurka, Mikolaj Jankowski, Deniz Gündüz

Recent works have shown that the task of wireless transmission of images can be learned with the use of machine learning techniques.

Coded Computation across Shared Heterogeneous Workers with Communication Delay

no code implementations23 Sep 2021 Yuxuan Sun, Fan Zhang, Junlin Zhao, Sheng Zhou, Zhisheng Niu, Deniz Gündüz

In this work, we consider a multi-master heterogeneous-worker distributed computing scenario, where multiple matrix multiplication tasks are encoded and allocated to workers for parallel computation.

Distributed Computing

Fast Federated Edge Learning with Overlapped Communication and Computation and Channel-Aware Fair Client Scheduling

no code implementations14 Sep 2021 Mehmet Emre Ozfatura, Junlin Zhao, Deniz Gündüz

We consider federated edge learning (FEEL) over wireless fading channels taking into account the downlink and uplink channel latencies, and the random computation delays at the clients.

Fairness

Variational Leakage: The Role of Information Complexity in Privacy Leakage

1 code implementation5 Jun 2021 Amir Ahooye Atashin, Behrooz Razeghi, Deniz Gündüz, Slava Voloshynovskiy

We study the role of information complexity in privacy leakage about an attribute of an adversary's interest, which is not known a priori to the system designer.

Representation Learning

Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraints

no code implementations31 May 2021 Yuxuan Sun, Sheng Zhou, Zhisheng Niu, Deniz Gündüz

In this work, we consider an over-the-air FEEL system with analog gradient aggregation, and propose an energy-aware dynamic device scheduling algorithm to optimize the training performance under energy constraints of devices, where both communication energy for gradient aggregation and computation energy for local training are included.

Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs

1 code implementation25 May 2021 Mohammad Malekzadeh, Anastasia Borovykh, Deniz Gündüz

It is known that deep neural networks, trained for the classification of non-sensitive target attributes, can reveal sensitive attributes of their input data through internal representations extracted by the classifier.

Knowledge Distillation

Dopamine: Differentially Private Federated Learning on Medical Data

1 code implementation27 Jan 2021 Mohammad Malekzadeh, Burak Hasircioglu, Nitish Mital, Kunal Katarya, Mehmet Emre Ozfatura, Deniz Gündüz

While rich medical datasets are hosted in hospitals distributed across the world, concerns on patients' privacy is a barrier against using such data to train deep neural networks (DNNs) for medical diagnostics.

Federated Learning

Bandwidth-Agile Image Transmission with Deep Joint Source-Channel Coding

no code implementations26 Sep 2020 David Burth Kurka, Deniz Gündüz

We propose deep learning based communication methods for adaptive-bandwidth transmission of images over wireless channels.

Distributed Deep Reinforcement Learning for Functional Split Control in Energy Harvesting Virtualized Small Cells

no code implementations7 Aug 2020 Dagnachew Azene Temesgene, Marco Miozzo, Deniz Gündüz, Paolo Dini

We formulate the corresponding grid energy and traffic drop rate minimization problem, and propose a distributed deep reinforcement learning (DDRL) solution.

Multi-agent Reinforcement Learning

DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedback

4 code implementations25 Nov 2019 David Burth Kurka, Deniz Gündüz

It is well known that separation is not optimal in the practical finite blocklength regime; however, there are no known practical joint source-channel coding (JSCC) schemes that can exploit the feedback signal and surpass the performance of separation-based schemes.

Energy-Aware Analog Aggregation for Federated Learning with Redundant Data

no code implementations1 Nov 2019 Yuxuan Sun, Sheng Zhou, Deniz Gündüz

In this work, we consider analog aggregation to scale down the communication cost with respect to the number of workers, and introduce data redundancy to the system to deal with non-i. i. d.

Federated Learning

Deep Convolutional Compression for Massive MIMO CSI Feedback

no code implementations2 Jul 2019 Qianqian Yang, Mahdi Boloursaz Mashhadi, Deniz Gündüz

In comparison with previous works, the main contributions of DeepCMC are two-fold: i) DeepCMC is fully convolutional, and it can be used in a wide range of scenarios with various numbers of sub-channels and transmit antennas; ii) DeepCMC includes quantization and entropy coding blocks and minimizes a cost function that accounts for both the rate of compression and the reconstruction quality of the channel matrix at the BS.

Quantization

A Reinforcement Learning Approach to Age of Information in Multi-User Networks

no code implementations1 Jun 2018 Elif Tuğçe Ceran, Deniz Gündüz, András György

Scheduling the transmission of time-sensitive data to multiple users over error-prone communication channels is studied with the goal of minimizing the long-term average age of information (AoI) at the users under a constraint on the average number of transmissions at the source node.

The Multi-layer Information Bottleneck Problem

no code implementations14 Nov 2017 Qianqian Yang, Pablo Piantanida, Deniz Gündüz

Based on information forwarded by the preceding layer, each stage of the network is required to preserve a certain level of relevance with regards to a specific hidden variable, quantified by the mutual information.

Content-Level Selective Offloading in Heterogeneous Networks: Multi-armed Bandit Optimization and Regret Bounds

no code implementations23 Jul 2014 Pol Blasco, Deniz Gündüz

It is shown that the proposed algorithms learn the popularity profile quickly for a wide range of system parameters.

Cannot find the paper you are looking for? You can Submit a new open access paper.