====== Tutorial and workshop on Explainable and Robust AI for Industry 4.0 & 5.0 (X-RAI) ====== {{ :xrai:ai-boost-f6s-logo.jpg?200|}} The X-RAI tutorial & workshop convenes industrial AI professionals and explainability experts to explore XAI developments and applications in industrial settings. Participants engage with the latest research, best practices, and challenges, fostering collaboration between researchers and engineers. Integrating explainability into Industry 4.0 and 5.0 ensures AI system reliability, trustworthiness, and transparency. While focusing on industrial applications, X-RAI encourages submissions applying various XAI paradigms across domains like healthcare and decision-making. The 1st edition of X-RAI will be at the [[https://2024.ecmlpkdd.org/|ECML-PKDD 2024]] conference. ===== Organizers ===== * Sepideh Pashami, Halmstad University and RISE, Sweden, sepideh.pashami@hh.se * Joao Gama, University of Porto, Porto, Portugal, jgama@fep.up.pt * Bruno Veloso, University of Porto, Porto, Portugal, bveloso@gmail.com * Rita P. Ribeiro, University of Porto, Porto, Portugal, rpribeiro@fc.up.pt * Grzegorz J. Nalepa, Jagiellonian University, Krakow, Poland, gjn@gjn.re * Szymon Bobek, Jagiellonian University, Krakow, Poland, szymon.bobek@uj.edu.pl {{:xrai:uj-logo.jpg?200 |}}{{:xrai:halmstad-logo.svg?200|}}{{:xrai:porto-logo.jpg?200|}} {{:xrai:rise.svg ?200 }} ==== Keynote Speaker ==== {{:xrai:raina.jpeg?200 |}} **Speaker**: Rafia Inam, Senior Research Manager, at Ericsson AB and Adjunct Professor, at KTH Royal Institute of Technology **Title**: Use of Explainable AI in Telcom domain **Biogram**: Rafia Inam is a senior research manager at Ericsson Research and Adjunct Professor at KTH in research area Trustworthy Artificial Intelligence, Sweden. She has conducted research for Ericsson for the past 8 years on 5G for industries, 5G network slices and management, using AI for automation, service modeling for Intelligent Transport Systems. She is specialized in automation and safety for CPS and collaborative robots, trustworthy AI, explainable AI, explainable RL, risk assessment and mitigations using AI methods, reusability of real-time software. She wonEricsson Top Performance Competition 2021 on her work on AI for 5G network slice assurance, and was awardedEricsson Key Impact Award 2020,and Key contributor award 2020, 2023,. Rafia received her Ph.D. from Mälardalen University, Sweden, in 2014 on predictable real-time embedded software. She is a Program Committee member, referee, guest editor for several international conferences and journals. Rafia has co-authored 40+ refereed scientific publications and 55+ patent families. She has wonbest paper awards on her two papers: “Towards automated service-oriented lifecycle management for 5G networks”, at the IEEE’s 9th International Workshop on Service Oriented Cyber-Physical Systems in Converging Networked Environments (SOCNE) in 2015, and “Support for Hierarchical Scheduling in FreeRTOS” in 16th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA’11), September 2011. ===== Tutorial Schedule ===== ^ Time ^ Topic ^ | 09:00 - 09:10 | Introduction | | 09:10 - 10:10 | AI for Industrial Applications such as Predictive Maintenance | | 10:10 - 11:00 | Explainable AI, including Types of Explanations and Evaluations | ^^ | 11:00 - 11:20 | Break | ^^ | 11:20 - 11:50 | Robustness in Machine Learning | | 11:50 - 12:20 | Metro Train Use Case and Neurosymbolic Explanation | | 12:20 - 12:35 | Steel Plant Use Case | | 12:35 - 12:50 | Commercial Vehicle Use Case | | 12:50 - 13:00 | Discussion and Open Questions | ==== Workshop Schedule ==== The workshop will take place on Friday, 13th of September 2024. ^Time^Title^Speaker^ | 14:00-14:50 |**Keynote: Use of Explainable AI in Telcom domain**| Rafia Inam| ^^ | 14:50-15:00 | **Break**|| ^^ | 15:00-15:20 | **Edge-MixShap: Shapley Value Attributed Explainable and Robust Model for Cardiovascular Disease Classification Using Electrocardiogram** | Arijit Ukil | | 15:20-15:40 | **A SAT-based approach to rigorous verification of Bayesian networks** |Ignacy Stępka| | 15:40-16:00 | **Forecasting Auxiliary Energy Consumption for Electric Heavy-Duty Vehicles** | Yuantao Fan| ===== Workshop information ====== ==== Important Dates ==== * **Submission Deadline**: 2024-06-15 2024-06-22 * **Author Notification**: 2024-07-15 * **Cemera Ready**: 2024-07-29 * **Workshop Date**: 2024-09-13 ==== Aims and Scope ==== The X-RAI tutorial & workshop aims to bring industrial AI professionals together with explainability experts to discuss the latest developments in XAI and their practical applications as well as theoretical works aiming at solving real-life problems in industrial settings. The tutorial & workshop will provide an opportunity for attendees to learn about the latest research, best practices, and challenges in this area. It is an opportunity to bridge researchers and engineers to discuss emerging topics and the newest trends. The integration of explainability in Industry 4.0 and 5.0 is crucial to ensure AI systems' reliability, trustworthiness, transparency and robustness. Although in X-RAI we focus mainly on Industrial applications, we are also encouraging to submit works that apply different paradigms of XAI as a means of solving particular problems in many different domains such as, healthcare, planning, decision making, etc. Each of these domains use different types of data, which require different techniques to display the model explanations properly. In this regard, it is common to find heatmaps on top of images highlighting the most important pixels for the model prediction, but the analogous for other types of data such as tabular data, time series or graphs is not so well studied. Thus, works that describe visual integrations of model explanations for other types of data rather than images and language will also be of interest in the session. We also focus on application of XAI methods in the machine learning/data mining pipeline in order to aid data scientists in building better AI systems. Such applications include, but are not limited to: feature engineering with XAI, feature and model selection with XAI, evaluation and visualization of ML/DM training process with XAI. Finally, we are also interested in the development of tools that integrate in a transparent and easy way the use of XAI methods, within the current popular machine & deep learning libraries. ==== Topics of interest ==== Overall, we are interested in receiving papers related to the following topics which include but are not limited to: * XAI in the context of Industry 4.0 & 5.0 * Ethical considerations in industrial deployment of AI * AI transparency and accountability in smart factories * Explainable systems fusing various sources of industrial information * Exploring XAI in performance and efficiency of industrial systems * Industrial use cases for XAI * Challenges and future directions for XAI in the industry * Evaluating the robustness * Challenges of building robust and reliable AI * Novel methods to improve robustness both for adversarial and out of distribution * Robustness requirements in critical domains like health care * XAI for predictive maintenance * Forecasting of product and process quality * Explainable anomaly detection * Data and information fusion in the industrial XAI context * Automatic process optimisation * Industrial process monitoring and modeling * Visual analytics and interactive machine learning * Decision-making assistance and resource optimisation * Planning under uncertainty * Analysis of usage patterns Real-world applications such as: * Manufacturing systems * Production processes and factories of the future * Energy and power systems and networks * Transport systems * Power generation and distribution systems * Intrusion detection and cyber security * Internet of Things * Big Data challenges in the digital transition * Healthcare equipment * Smart cities ==== Program Committee (tentative) ==== * Javier, del Ser,Tecnalia, Spain * Ricardo, Aler,Universidad Carlos III de Madrid, Spain * Felix José Fuentes, Hurtado,Universidad Politécnica de Valencia, Spain * Juan, Pavón,Universidad Complutense de Madrid, Spain * Francesco, Piccialli,University of Naples Federico II, Italy * Salvatore, Cuomo,University of Naples Federico II, Italy * Edoardo, Prezioso,University of Naples Federico II, Italy * Federico, Gatta,University of Naples Federico II, Italy * Fabio, Giampaolo,University of Naples Federico II, Italy * Stefano, Izzo,University of Naples Federico II, Italy * Alejandro, Martin,Universidad Politécnica de Madrid, Spain * Angel, Panizo,Universidad Politécnica de Madrid, Spain * Javier, Huertas,Universidad Politécnica de Madrid, Spain * Martin, Atzmueller, Universitat Osnabruck, Germany * Kacper, Sokół, University of Bristol, UK * Sławomir, Nowaczyk, Halmstad University, Sweden * Jerzy, Stefanowski, Poznan University of Technology, Poland * Marek, Sikora, Silesian University of Technology, EMAG Institute * Jose, Palma, University of Murcia, Spain * Michal, Choras, UTP University of Science and Technology, Poland * Boguslaw ,Cyganek, AGH University of Science and Technology in Krakow, Poland * Michał, Araszkiewicz, Jagiellonian University, Poland * Timos, Kipouros, University of Cambridge, UK ==== Submission details ==== Please use the following link to submit your paper: [[https://cmt3.research.microsoft.com/ECMLPKDDWorkshops2024/| ECMLPKDDWorkshops2024]] The Workshops and Tutorials will be included in a joint Post-Workshop proceeding published by Springer Communications in Computer and Information Science, in 1-2 volumes, organised by focused scope and possibly indexed by WOS. Papers authors will have the faculty to opt-in or opt-out. We suggest workshop papers are prepared and submitted in the format: [[https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines|LNCS format]]. Full papers should follow the Springer format of regular ECML submissions and be no longer than 16 pages (including references). Following ECML review process, we will apply a double-blind review-process (author identities are not known by reviewers or area chairs; reviewers do see each other’s names). All papers need to be ‘best-effort’ anonymized. Papers must not include identifying information of the authors (names, affiliations, etc.), self-references, or links (e.g., GitHub, YouTube) that reveal the authors’ identities (e.g., references to own work should be given neutrally like other references, not mentioning ‘our previous work’ or similar). We strongly encourage making code and data available anonymously (e.g., in an anonymous Github repository, or Dropbox folder). The authors might have a (non-anonymous) pre-print published online, but it should not be cited in the submitted paper to preserve anonymity. Reviewers will be asked not to search for them. We recognize there are limits to what is feasible with respect to anonymization. For example, if you use data from your own organization and it is relevant to the paper to name this organization, you may do so.