ITEM Workshop 2024
IoT, Edge, and Mobile for Embedded Machine Learning
Workshop collocated with ECML-PKDD 2024, Vilnius, Lithuania, September 9, 2024
News
Aug 5, 2024: Keynote speakers and program posted!
Jul 25, 2024: workshop scheduled by ECML to Sept 9, 2024
June 6, 2024: Submission DL extended to June 22, 2024 at 23:59 AoE
May 13, 2024: Update on TPC and submission site!
March 9, 2024: ITEM in its fifth edition has been accepted at ECML-PKDD2024, and is calling for papers! Please see details below for early information about format and important dates.
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 of neural networks for inference deployment, including methods for quantization (including binarization), pruning, knowledge distillation, structural efficiency and neural architecture search
Hardware support for novel ML architectures beyond CNNs, e.g., transformer models
Tractable models beyond neural networks
Learning on edge devices, including federated and continuous learning
Trading among prediction quality (accuracy), efficiency of representation (model parameters, data types for arithmetic operations and memory footprint in general), and computational efficiency (complexity of computations)
Automatic code generation from high-level descriptions, including linear algebra and stencil codes, targeting existing and future instruction set extensions
Tool driven optimizations up from ML model level down to instruction level, automatically adapted to the current hardware requirements
Understanding the difficulties and opportunities using common ML frameworks with marginally supported devices
Exploring new ML models designed to use on designated device hardware
Future emerging processors and technologies for use in resource-constrained environments, e.g., RISC V, embedded FPGAs, or analogue technologies
Applications and experiences from deployed use cases requiring embedded ML
New and emerging applications that require the use of ML on resource-constrained hardware
Energy efficiency of ML models created with distinct optimization techniques
Security/privacy of embedded ML
New benchmarks suited to edge and embedded devices
Important Dates
Workshop paper submission deadline: June 22, 2024 at 23:59 AoE (old: June 15, 2024)
Workshop Paper Author Notification: July 15, 2024
Camera-ready deadline: approx. July 31, 2024 (depending on conference organization)
Workshop date: full day, in between Sept 9 and 13, 2024 (depending on conference organization)
Submission
Papers must be written in English and formatted according to the Springer LNCS guidelines. An author kit can be found here: https://klevas.mif.vu.lt/~linp/ecmlpkdd2024/ECML_PKDD_2024_Author_Kit.zip
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-PKDD2024 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. Papers authors will have the faculty to opt-in or opt-out. Online submission: https://cmt3.research.microsoft.com/ECMLPKDDWorkshops2024 (please ensure you choose the "ITEM" track)
Program Committee
Dolly Sapra, University of Amsterdam, Netherlands
Masoud Daneshtal, Mälardalen University, Sweden
Jose Cano Reyes, University of Glasgow, UK
Manuel Dolz, Universitat Jaume I, Spain
Axel Jantsch, TU Vienna, Austria
Sébastien Rumley, University of Applied Sciences Western Switzerland
Jürgen Teich, University of Erlangen-Nuremberg, Germany
Enrique Quintana-Ortí, Technical University of Valencia, Spain
Pinar Tözün, IT University of Copenhagen, Denmark
Mattias O'Nils, Mittuniversitetet, Sweden
Manuele Rusci, KU Leuven, Belgium
Arya Mazaheri, TU Darmstadt, Germany
Grace Zhang, TU Darmstadt, Germany
Martin Andraud, UC Louvain, Belgium
Herman Engelbrecht, University of Stellenbosch, South Africa
Diana Goehringer, TU Dresden, Germany
Jürgen Becker, KIT, Germany
Nicolas Weber, NEC Laboratories Europe, Germany
Burghard Ringlein, IBM Zurich, Switzerland
Dennis Rieber, Axelera, Germany
Program
Workshop takes places on Sept 9, 2024, from 09:00 to 18:00 (full-day workshop). Breaks are aligned with ECML's schedule.
09:00-11:00 Session 1
Welcome and introduction
Keynote by Manuele Rusci: Adaptive on-device deep-learning for audio and visual sensors at the extreme-edge
Contributed article: Djajapermana, Mikhael - Hybrid Convolution and Vision Transformer NAS Search Space for TinyML Image Classification
Contributed article: Sadaqa, Ahmed - Compressing CNN models for resource-constrained systems by channel and layer pruning
11:00-11:30 Coffee break
11:30 - 13:00 Session 2
Contributed article: Vasilache, Alexandru; Nitzsche, Sven; Floegel, Daniel; Schuermann, Tobias; von Dosky, Stefan; Bierweiler, Thomas; Mussler, Marvin ; Kaelber, Florian; Hohmann, Soeren; Becker, Jürgen - Low-Power Vibration-Based Predictive Maintenance for Industry 4.0 using Neural Networks: A Survey
Contributed article: Leslin, Jelin; Trapp, Martin; Andraud, Martin - Mixed precision HW acceleration in PCs
Contributed article: Schnöll, Daniel; Wess, Matthias; Dallinger, Dominik; Bittner, Matthias; Jantsch, Axel - Towards Optimal Implementations of Neural Networks on Micro-Controller
13:00-14:00 Lunch break
14:00-16:00 Session 3
Keynote by Grace Li Zhang: Efficient and Robust Hardware for Neural Networks
Contributed article: Puślecki, Tobiasz T; Walkowiak, Krzysztof - On The Dynamic Ensemble Selection for TinyML-based Systems - a Preliminary Study
Contributed article: Barley, Daniel; Froening, Holger - Less Memory Means smaller GPUs: Backpropagation with Compressed Activations
16:00 - 16:30 Coffee break
16:30 - 18:00 Session 4
Contributed article: Kummerow, Arne; Weis, Torben - Resilient Decentralized Reinforcement Learning: A Reconstruction Approach
Discussion & next steps
Wrap-up
Synergies
This workshop is envisioned as a counterpart to the highly successful workshop series on embedded machine learning (WEML), held at Heidelberg University (for the latest edition, see https://www.deepchip.org/weml2023.). 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
Holger Fröning, Heidelberg University, Germany (holger.froening(at)ziti.uni-heidelberg.de)
Gregor Schiele, University of Duisburg-Essen (gregor.schiele(at)uni-due.de)
Franz Pernkopf, Graz University of Technology, Austria (pernkopf(at)tugraz.at)
Michaela Blott, XILINX Research, Dublin, Ireland (michaela.blott(at)amd.com)
Program Co-Chair
Kazem Shekofteh, Heidelberg University, Germany (kazem.shekofteh@ziti.uni-heidelberg.de)