Multiple Access

Multiple access techniques aim to efficiently share limited communication resources among multiple devices, a crucial challenge in distributed computing and the Internet of Things. Current research heavily focuses on optimizing federated learning over wireless networks, employing over-the-air computation and various multiple access schemes (e.g., TDMA, random access, NOMA) to aggregate data efficiently while mitigating interference and noise. This involves developing novel algorithms like deep reinforcement learning for resource allocation and robust gradient aggregation methods to improve model training accuracy and convergence speed. These advancements are vital for enabling large-scale distributed applications, particularly in areas like edge intelligence and the Metaverse, by reducing communication bottlenecks and enhancing system efficiency.

Papers

June 8, 2022

Scalable Joint Learning of Wireless Multiple-Access Policies and their Signaling
Mateus P. Mota, Alvaro Valcarce, Jean-Marie Gorce
Reinforcement Learning Multi Agent Reinforcement Learning Joint Learning Abnormal Signal Multiple Access Channel Access

May 22, 2022

Data-aided Active User Detection with a User Activity Extraction Network for Grant-free SCMA Systems
Minsig Han, Ameha T. Abebe, Chung G. Kang
Supervised Autoencoder Autoencoder Model Random Access Multiple Access

May 6, 2022

How to Minimize the Weighted Sum AoI in Multi-Source Status Update Systems: OMA or NOMA?
Jixuan Wang, Deli Qiao
Power Allocation Multiple Access Age of Information Orthogonal Multiple Access Multi Source Information Fusion

May 2, 2022

Model-based Deep Learning Receiver Design for Rate-Splitting Multiple Access
Rafael Cerna Loli, Onur Dizdar, Bruno Clerckx, Cong Ling
Multiple Access Interference Cancellation Interference Channel Rate Splitting Interference Management

March 29, 2022

Over-the-Air Federated Learning via Second-Order Optimization
Peng Yang, Yuning Jiang, Ting Wang, Yong Zhou, Yuanming Shi, Colin N. Jones
Air Federated Learning Federated Optimization Local Convergence Multiple Access Second Order Optimization Novel Over the Air Second

January 24, 2022

A Machine Learning Framework for Distributed Functional Compression over Wireless Channels in IoT
Yashas Malur Saidutta, Afshin Abdi, Faramarz Fekri
Machine Learning Framework Multiple Access Wireless Channel Functional Compression

Multiple Access

Papers

Scalable Joint Learning of Wireless Multiple-Access Policies and their Signaling

Data-aided Active User Detection with a User Activity Extraction Network for Grant-free SCMA Systems

How to Minimize the Weighted Sum AoI in Multi-Source Status Update Systems: OMA or NOMA?

Model-based Deep Learning Receiver Design for Rate-Splitting Multiple Access

Over-the-Air Federated Learning via Second-Order Optimization

A Machine Learning Framework for Distributed Functional Compression over Wireless Channels in IoT