Wireless Communications for Distributed Intelligence 

Wireless Communications for Distributed Intelligence.
Picture above: Two possible network topologies for distributed Machine Learning. Left: parameter-server-based. Right: fully decentralized.

Distributed and networked intelligent systems will play a crucial role in our highly digitalized human society. In the foreseeable future, data used for artificial intelligence (AI) tasks may bypass human-perceived applications and become the dominant source of mobile data traffic. This paradigm shift calls for new communication designs to enable efficient data collection, processing, transmission, and utilization in distributed AI systems supported by wireless connectivity.

With 5G becoming a reality, the next question is: what will 6G bring? Mobile cellular standards are updated every decade, and their development is always driven by evolving application demands and user scenarios. From 1G to 5G, applications have evolved from simple phone calls and text messaging to online browsing, video streaming, and gaming.

Looking ahead to 6G, we expect AI-driven data to surpass human-centric applications and become the dominant source of mobile traffic. Related applications include autonomous vehicles, industrial automation, virtual/augmented reality, and E-health systems. As a result, next-generation wireless networks must evolve to meet the demands of AI-driven data traffic.

From centralized to decentralized Machine Learning systems

Conventionally, Machine Learning (ML) algorithms are performed in a centralized unit where the training data sets are stored. In many applications, the training data are collected from different user devices and those data might contain private information about the users. Due to the privacy concerns in centralized ML systems, decentralized ML has emerged as an alternative solution that allows user devices to perform intelligent information processing locally based on their raw data or observations, without uploading them to a centralized server/cloud.

For any distributed system that relies on signaling and information exchange between distributed nodes to achieve some collective goals, wireless connectivity will always be the performance bottleneck. In a wireless network, the amount of information bits that can be reliably delivered is limited by the available communication resources (time, frequency, space). An efficient communication protocol and resource allocation design for distributed ML systems can make a significant difference than blindly applying the conventional rate-driven wireless design.

Research Activities

Our current research directions in this project are:

  • Resource allocation for federated edge learning
  • Over-the-Air (OtA) computation for distributed learning and estimation
  • Communication-efficient designs for distributed consensus and optimization.

The specific topics cover data compression, resource allocation, signal processing, medium access control, privacy, and security aspects of distributed intelligence over wireless networks. Broadly speaking, our research group aims to identify new topics and interesting problems within the intersection of communication theory, distributed algorithms, and machine learning.

Acknowledgements: our research group is supported by ELLIIT, Swedish Research Council (VR), Wallenberg Foundations, and Zenith.

Researchers

Publications

2025

Daniel Pérez Herrera, Zheng Chen, Erik G Larsson (2025) Faster Convergence With Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning Over Wireless Networks IEEE Open Journal of the Communications Society, Vol. 6, p. 1497-1511 (Article in journal) Continue to DOI
Chung-Hsuan Hu, Zheng Chen, Erik G Larsson (2025) Energy-Efficient Federated Edge Learning With Streaming Data: A Lyapunov Optimization Approach IEEE Transactions on Communications, Vol. 73, p. 1142-1156 (Article in journal) Continue to DOI

2024

Daniel Pérez Herrera, Zheng Chen, Erik G Larsson (2024) Decentralized Learning over Wireless Networks with Broadcast-Based Subgraph Sampling ICC 2024 - IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, p. 932-937 (Conference paper) Continue to DOI
Themistoklis Charalambous, Zheng Chen, Christoforos N. Hadjicostis (2024) Distributed Average Consensus in Wireless Multi-Agent Systems with Over-the-Air Aggregation 2024 IEEE 25TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS, SPAWC 2024, p. 441-445 (Conference paper) Continue to DOI
David Nordlund, Jialing Liao, Zheng Chen (2024) Byzantine-Resilient Hierarchical Federated Learning with Clustered Over-The-Air Aggregation 2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW 2024, p. 715-719 (Conference paper) Continue to DOI

About the division

About the department