D2D Data

Device-to-device (D2D) data communication is revolutionizing distributed machine learning, particularly federated learning, by enabling efficient model training across numerous devices without relying solely on a central server. Current research focuses on optimizing D2D data transfer for federated learning, addressing challenges like network heterogeneity, unreliable connections, and data distribution skew through techniques such as topology learning, intelligent device sampling, and coded matrix computations. These advancements aim to improve model accuracy, reduce resource consumption (energy and communication), and enhance privacy, with significant implications for applications ranging from autonomous navigation to large-scale data analysis.

Papers

October 23, 2024

Dynamic Spectrum Access for Ambient Backscatter Communication-assisted D2D Systems with Quantum Reinforcement Learning
Nguyen Van Huynh, Bolun Zhang, Dinh-Hieu Tran, Dinh Thai Hoang, Diep N. Nguyen, Gan Zheng, Dusit Niyato, Quoc-Viet Pham
Quantum Reinforcement Learning Wireless Signal Spectrum Access D2D Data Backscatter Network

December 21, 2023

Topology Learning for Heterogeneous Decentralized Federated Learning over Unreliable D2D Networks
Zheshun Wu, Zenglin Xu, Dun Zeng, Junfan Li, Jie Liu
Decentralized Federated Learning Topological Learning Discrepancy Aware Device to Device D2D Data

November 7, 2023

Device Sampling and Resource Optimization for Federated Learning in Cooperative Edge Networks
Su Wang, Roberto Morabito, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton
Wireless Network Edge Cloud Fast Sampling Task Offloading Resource Optimization D2D Data

July 6, 2023

Context-Aware Configuration and Management of WiFi Direct Groups for Real Opportunistic Networks
Valerio Arnaboldi, Mattia Giovanni Campana, Franca Delmastro
Automatic WiFi Device to Device Opportunistic Routing D2D Data

March 10, 2023

TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets
Weixin Chen, Dawn Song, Bo Li
Diffusion Model Trojan Attack D2D Data Diverse Target

February 23, 2023

Coded Matrix Computations for D2D-enabled Linearized Federated Learning
Anindya Bijoy Das, Aditya Ramamoorthy, David J. Love, Christopher G. Brinton
Straggler Mitigation Offloading Robot Functionality Coded Computing D2D Data

November 8, 2022

DNN Filter for Bias Reduction in Distribution-to-Distribution Scan Matching
Matthew McDermott, Jason Rife
Point Cloud Distribution Alignment Bias Reduction Cloud Registration D2D Data

D2D Data

Papers

Dynamic Spectrum Access for Ambient Backscatter Communication-assisted D2D Systems with Quantum Reinforcement Learning

Topology Learning for Heterogeneous Decentralized Federated Learning over Unreliable D2D Networks

Device Sampling and Resource Optimization for Federated Learning in Cooperative Edge Networks

Context-Aware Configuration and Management of WiFi Direct Groups for Real Opportunistic Networks

TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets

Coded Matrix Computations for D2D-enabled Linearized Federated Learning

DNN Filter for Bias Reduction in Distribution-to-Distribution Scan Matching