The feasibility and scalability of Artificial Intelligence and Machine Learning (AI/ML) algorithms at the edge networks faces three principal challenges: (i) communication and computation cost, (ii) heterogeneity and time-varying nature of edge devices, and (iii) heightened security and privacy concerns given the vulnerability of edge devices. In this context, research is needed to tailor AI/ML mechanisms to edge computing to harvest heterogeneous resources including computing power, storage, battery, networking resources, etc., scattered across end devices, edge servers, and cloud with minimum amount of communication cost. Despite the rapidly growing scientific body of work to implement AI/ML mechanisms at the edge networks, the area is still nascent, and is conducted by many researchers whose instincts come from classical applications such as communications and networking. By exposing the challenges and ideas of modern AI/ML systems to edge computing, this workshop aims to provide a unique opportunity to shape the growth of the field and maximize the chances of its impact to meet AI/ML with edge computing.

This workshop will explore the AI/ML mechanism over edge networks by exploiting techniques including communication efficient distributed AI/ML, conditional computation, and decentralized learning. We invite researchers to contribute their novel research results that advance the development of distributed AI/ML at the resource-constrained edge.

Topics of interest include but are not limited to:

-   Communication-Efficient Distributed AI/ML.

-   Model-Distributed Training and Inference

-   Split Learning

-   Conditional Computation at the Edge

-   Decentralized Learning at the Edge

-   Random Walk-Based Learning

-   Coded Computation for Distributed AI/ML

-   Security and Privacy for Distributed AI/ML

-   AI/ML-Based Resource management at the Edge

-   Trustworthy AI for Resource Constrained Edge

-   Dynamic Edge Neural Networks

-   Reinforcement Learning for Network Optimization

-   Multi-Agent Reinforcement Learning

Paper Submissions:

Authors are invited to submit original unpublished papers not under review elsewhere. Submissions will be subjected to a peer-review process. All submissions should be written in English with draft papers up to six (6) printed pages in length, two-column, single-spaced with 10-point font on US Letter paper. Final papers that exceed six (6) pages will be assessed a per-page over-length charge of $150/page, up to a maximum of eight (8) total pages. Please check the manuscript requirements for further details. Please submit your papers via Edas. 

Workshop General Chairs:

Matt Dwyer, Army Research Lab 

Hulya Seferoglu, University of Illinois Chicago

Raffaele Galliera, IHMC

Workshop Technical Program Chairs:

Erdem Koyuncu, University of Illinois Chicago 

Salim El Rouayheb, Rutgers University 

Scott Brown, Army Research Lab 

Important Dates:

Paper Submission:         August 20, 2025