News

• March 04, 2026: Announcement - ITEM in its seventh edition has been accepted at ECML-PKDD2026. Initialisation of the homepage!

Overview

Local and embedded machine learning (ML) is a key component for real-time data analytics in upcoming computing environments like the Internet of Things (IoT), edge computing and mobile ubiquitous systems. The goal of the ITEM workshop is to bring together experts, researchers and practitioners from all relevant communities, including ML, hardware design and embedded systems, IoT, edge, and ubiquitous / mobile computing. Topics of interest include compression techniques for existing ML models, new ML models that are especially suitable for embedded hardware, tractable models beyond neural networks, federated learning approaches, as well as automatic code generation, frameworks and tool support. The workshop is planned as a combination of invited talks, paper submissions, as well as open-table discussions. 

Keywords: embedded machine learning, pervasive intelligent devices, real-time data analytics, uncertainty and robustness

About the Workshop

There is an increasing need for real-time intelligent data analytics, driven by a world of Big Data, and the society’s need for pervasive intelligent devices, such as wearables for health and recreational purposes, smart city infrastructure, e-commerce, Industry 4.0, and autonomous robots. Most applications share facts like large data volumes, real-time requirements, limited resources including processor, memory, network and possibly battery life. Data might be large but possibly incomplete and uncertain. Notably, often powerful cloud services can be unavailable, or not an option due to latency or privacy constraints. For these tasks, Machine Learning (ML) is among the most promising approaches to address learning and reasoning under uncertainty. Examples include image and speech processing, such as image recognition, segmentation, object localization, multi-channel speech enhancement, speech recognition, signal processing such as radar signal denoising, with applications as broad as robotics, medicine, autonomous navigation, recommender systems, etc.

To address uncertainty, limited data, and to improve in general the robustness of ML, new methods are required, with examples including Bayesian approaches, sum-product networks, transformer networks, graph-based neural networks, deep ensembles and many more. One can observe that, compared with deep convolutional neural networks, computations can be fundamentally different, compute requirements can substantially increase, and underlying properties like structure in computation are often lost. 

As a result, we observe a strong need for new methods to address the requirements of emerging ML applications deployed in the real-world, such as uncertainty, robustness, and limited data. In order to not hinder the deployment of such methods on various computing devices, and to address the gap in between application and compute hardware, we furthermore need a variety of tools. 

As such, this workshop addresses the complete vertical stack of ML deployment, and as such gears to gather new ideas and concepts on 

• ML methods for real-world deployment, 

• methods for compression and related complexity reduction tools, 

• associated tooling like compilers and mappers,

• and dedicated hardware for emerging ML applications

Topics of Interest

Topics of particular interest include, but are not limited to:

• Compression techniques for embedded ML, e.g., quantization, pruning, and knowledge distillation 

• Techniques for hardware-aware neural architecture search

• Hardware support for novel ML architectures beyond CNNs, e.g., Transformer models, LLMs

• Techniques for learning ML models in hardware, including federated and continuous learning

• Trading among application metrics (accuracy, error) and hardware costs / complexity (memory footprint, latency, resources)

• Techniques / Tools for compiling ML models from high-level descriptions to hardware targets (include optimization feedback), e.g., intermediate representation, instruction sets, templates

• Difficulties and opportunities using common ML frameworks with marginally supported devices

• Exploring new ML models designed to be used on designated device hardware

• Future emerging processors and computing technologies, e.g., RISC-V, embedded FPGAs, In-Memory Computing, Analogue Computing, Photonic Computing 

• Applications and experiences from deployed use cases requiring embedded ML

• New and emerging applications that require the use of ML on resource-constrained hardware

• Probabilistic ML for embedded systems: training, compression, approximation, and efficient hardware mapping

• Deployment of an end-to-end AI processing pipeline into real hardware and applications

• Optimization techniques to unroll embedded ML in resource-constrained environments

• Performance evaluation and benchmarking of ML accelerators on embedded and edge workloads

Important Dates

• Opening Submission: March 31, 2026 (may be delayed due to conference) 

• Submission deadline: June 5, 2026 at 23:59 AoE  (updating with conference organization)

• Acceptance notification: June 26, 2026 (updating with conference organization)

• Camera-ready deadline: July 10, 2026 (updating with conference organization)

• Workshop date: Sept 7, 2026 (First day of the conference) or Sept 11, 2026 (Last day of the conference)

Submission

Papers must be written in English and formatted according to the Springer LNCS guidelines. An author kit can be found here [Link], 

Submissions may not exceed 12 pages in PDF format for full papers, respectively 6 pages for short papers, including figures and references. Submitted papers must be original work that has not appeared in and is not under consideration for another conference or journal. Please prepare submissions according to single-blind standards. Work in progress is welcome, but first results should be made available as a proof of concept. Submissions only consisting of a proposal will be rejected. 

ECML-PKDD 2026 will organize joint post-workshop proceeding published by Springer Communications in Computer and Information Science, in 1-2 volumes, organized by focused scope and possibly indexed by WOS. Please upload your manuscript in Microsoft CMT system in the Workshop Tracks.

Program Committee (Tentiative)

Call for Reviewer is in Preparation!

Program

This workshop will be hold as full-day format. We will publish further informations after the review process.

Synergies

This workshop is envisioned as a counterpart to the highly successful workshop series on embedded machine learning (WEML). The latest edition was held at University of Duisburg-Essen [Link]. The two workshop formats complement each other, as WEML is highly discussion-oriented, invitation-only, without requirements on scientific novelty, results or publications. In contrast, ITEM is envisioned as a high-quality academic outlet, including results demonstrating at least the potential of presented work, and with a healthy mix of peer-reviewed contributions and invited talks.

Organization

Co-Organizers

• Andreas Erbslöh, University of Duisburg-Essen, Germany (andreas.erbsloeh(at)uni-due.de)

• Kazem Shekofteh, Heidelberg University, Germany (kazem.shekofteh(at)ziti.uni-heidelberg.de) 

• Bernhard Klein, Heidelberg University, Germany (bernhard.klein(at)ziti.uni-heidelberg.de) 

• Tianheng Ling, University of Duisburg-Essen, Germany (tianheng.ling(at)uni-due.de) 

Advisory Board

• Holger Fröning, Heidelberg University, Germany (holger.froening(at)ziti.uni-heidelberg.de) 

• Gregor Schiele, University of Duisburg-Essen, Germany (gregor.schiele(at)uni-due.de)