Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
praxai:start [2022/03/10 09:05] – [Practical applications of explainable artificial intelligence methods (PRAXAI)] sbkpraxai:start [2023/08/02 06:29] (current) – [Important Dates] sbk
Line 3: Line 3:
 **PRAXAI webpage address is [[http://praxai.geist.re]]** **PRAXAI webpage address is [[http://praxai.geist.re]]**
  
-PRAXAI  special session at [[http://dsaa2022.dsaa.co/|The 9th IEEE International+PRAXAI  special session at [[https://conferences.sigappfr.org/dsaa2023/|The 10th IEEE International
 Conference on Data Science and Advanced Analytics]] focuses on bringing the research on Explainable Conference on Data Science and Advanced Analytics]] focuses on bringing the research on Explainable
 Artificial Intelligence (XAI) to actual applications and tools that help Artificial Intelligence (XAI) to actual applications and tools that help
Line 17: Line 17:
 daily work. daily work.
  
-The PRAXAI 2022 session is related to the [[https://www.hh.se/english/research/our-research/research-at-the-school-of-information-technology/technology-area-aware-intelligent-systems/research-projects-within-aware-intelligent-systems/xpm-explainable-predictive-maintenance.html|CHIST-ERA XPM]] project.+The PRAXAI 2023 session is related to the [[https://www.hh.se/english/research/our-research/research-at-the-school-of-information-technology/technology-area-aware-intelligent-systems/research-projects-within-aware-intelligent-systems/xpm-explainable-predictive-maintenance.html|CHIST-ERA XPM]] project.
    
 ===== Important Dates ===== ===== Important Dates =====
-  * **Submission Deadline**: June 12022 +  * **Submission Deadline**: <del>May 2</del> May 222023  
-  * **Notification**:  July 312022 +  * **Notification**: <del>July 10</del> July 242023  
-  * **Camera Ready Due**: August 152022+  * **Camera Ready Due**: <del>August 7</del> August 212023  
 +  * **Conference date**: October 9-13
  
 ===== Call for papers ===== ===== Call for papers =====
-  * TBA+  * {{ :praxai:praxai-2023-cfp.pdf |Call for Papers}} 
 + 
 ===== Submission Instructions ===== ===== Submission Instructions =====
  
-The length of each paper submitted to the Research and Application tracks should be no more than 10 pages, whereas the maximum number of pages is 2 for each abstract submitted to the Poster and Journal track. Both types of papers should be formatted following the standard 2-column U.S. letter style of IEEE Conference template. See the IEEE Proceedings Author Guidelines: http://www.ieee.org/conferences_events/conferences/publishing/templates.html, for further information and instructions.+The length of each paper submitted to the Research and Application tracks should be no more than 10 pages, formatted following the standard 2-column U.S. letter style of IEEE Conference template. See the IEEE Proceedings Author Guidelines: http://www.ieee.org/conferences_events/conferences/publishing/templates.html, for further information and instructions.
  
 All submissions will be double-blind reviewed by the Program Committee on the basis of technical quality, relevance to the scope of the conference, originality, significance, and clarity. The names and affiliations of authors must not appear in the submissions, and bibliographic references must be adjusted to preserve author anonymity. Submissions failing to comply with paper formatting and authors anonymity will be rejected without reviews. All submissions will be double-blind reviewed by the Program Committee on the basis of technical quality, relevance to the scope of the conference, originality, significance, and clarity. The names and affiliations of authors must not appear in the submissions, and bibliographic references must be adjusted to preserve author anonymity. Submissions failing to comply with paper formatting and authors anonymity will be rejected without reviews.
Line 34: Line 37:
 Authors are also encouraged to submit supplementary materials, i.e., providing the source code and data through a GitHub-like public repository to support the reproducibility of their research results. Authors are also encouraged to submit supplementary materials, i.e., providing the source code and data through a GitHub-like public repository to support the reproducibility of their research results.
  
-Electronic submission site: https://cmt3.research.microsoft.com/DSAA2022+Electronic submission site: [[https://easychair.org/my/conference?conf=dsaa2023|EasyChair]]
  
  
Line 40: Line 43:
  
 Explainable Artificial Intelligence (XAI) has become an inherent component of data mining (DM) and machine learning (ML) pipelines in the areas  where the insight into the decision process of an automated system is important.  Explainable Artificial Intelligence (XAI) has become an inherent component of data mining (DM) and machine learning (ML) pipelines in the areas  where the insight into the decision process of an automated system is important. 
 +
 Although explainability (or intelligibility) is not a new concept in AI, it has been most extensively developed over the last decade focusing mostly on explaining black-box models. Many successful frameworks were developed such as LIME, SHAP, LORE, Anchor, GradCam, DeepLift and others that aim at providing explanations and transparency to decisions made by machine learning models. Although explainability (or intelligibility) is not a new concept in AI, it has been most extensively developed over the last decade focusing mostly on explaining black-box models. Many successful frameworks were developed such as LIME, SHAP, LORE, Anchor, GradCam, DeepLift and others that aim at providing explanations and transparency to decisions made by machine learning models.
 +
 However, artificial intelligence systems in real-life applications are rarely composed of a single machine learning model, but rather are formed by a number of components orchestrated to work together for solving selected goals. Similarly, explainability  itself is a very broad concept that goes beyond explanation of machine learning algorithms, being more of a property of a system as a whole. However, artificial intelligence systems in real-life applications are rarely composed of a single machine learning model, but rather are formed by a number of components orchestrated to work together for solving selected goals. Similarly, explainability  itself is a very broad concept that goes beyond explanation of machine learning algorithms, being more of a property of a system as a whole.
 Thus, the goal of the XAI methods is not simply to provide an explanation of a decision made by a ML model, but use this explanation to achieve goals that are related to the primary goal of a system as a whole by improving its transparency, accountability, and interpretability. We believe that these properties can be achieved (and should be whenever possible)  by using interpretable models, knowledge-based explanations and human-in-the-loop interactive explanations (mediations). Explanations should be built in a context-aware manner that takes into consideration not only the goal of the system, but also the end-user of the explanation and the characteristics of the data. Thus, the goal of the XAI methods is not simply to provide an explanation of a decision made by a ML model, but use this explanation to achieve goals that are related to the primary goal of a system as a whole by improving its transparency, accountability, and interpretability. We believe that these properties can be achieved (and should be whenever possible)  by using interpretable models, knowledge-based explanations and human-in-the-loop interactive explanations (mediations). Explanations should be built in a context-aware manner that takes into consideration not only the goal of the system, but also the end-user of the explanation and the characteristics of the data.
 +
 Therefore, in this special session we focus on works that apply different paradigms of XAI as a means of solving particular problems in many different  domains such as manufacturing, 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. Therefore, in this special session we focus on works that apply different paradigms of XAI as a means of solving particular problems in many different  domains such as manufacturing, 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. 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 ===== ===== Topics of interest =====
- +  * Industry 4.0/5.0 and XAI
   * Model explanations verbalized in human-comprehensible natural language    * Model explanations verbalized in human-comprehensible natural language 
   * Explainable Reinforcement learning    * Explainable Reinforcement learning 
Line 62: Line 69:
   * Visualization of model explanations for different types of data apart from language and images (tabular data, time series, graphs, etc.)   * Visualization of model explanations for different types of data apart from language and images (tabular data, time series, graphs, etc.)
   * XAI software development and its integration into popular ML/DL libraries   * XAI software development and its integration into popular ML/DL libraries
 +  * Fairness and XAI
 +  * Ethics and XAI
 +  * Trust in XAI systems
 +  * XAI in real-world applications: case studies and success stories
 +
  
  
 ===== Program Committee (tentative) ===== ===== Program Committee (tentative) =====
 +  * Javier del Ser, Tecnalia
 +  * Eneko Osaba, Tecnalia
 +  * Ricardo Aler, Universidad Carlos III de Madrid
 +  * Felix José Fuentes Hurtado,Universidad Politécnica de Valencia
 +  * Alejandro Martin, Universidad Politécnica de Madrid, Spain
 +  * Angel Panizo, Universidad Politécnica de Madrid, Spain
 +  * Javier Huertas, Universidad Politécnica de Madrid, Spain
 +  * Juan Pavón, Universidad Complutense de Madrid
 +  * Francesco Piccialli,University of Naples Federico II
 +  * Salvatore Cuomo,University of Naples Federico II
 +  * Edoardo Prezioso,University of Naples Federico II
 +  * Federico Gatta,University of Naples Federico II
 +  * Fabio Giampaolo,University of Naples Federico II
 +  * Stefano Izzo,University of Naples Federico II
 +  * Martin Atzmueller, Universitat Osnabruck
 +  * Kacper Sokół, University of Bristol
 +  * Sławomir Nowaczyk, Halmstad University
 +  * Michal Choras, UTP University of Science and Technology
 +  * Bogusław Cyganek, AGH University of Science and Technology in Krakow
 +  * Timos Kipouros, University of Cambridge
 +  * Jerzy Stefanowski,  Poznan University of Technology, Poland
 +  * Hubert Baniecki, Warsaw University, Poland
 +  * Holzinger Andreas, Vienna University, Austria
 +  * Bastian Pfeifer, Medical University of Graz, Austria
 +  * Mustafa Cavuş, Eskisehir Technical University, Turkey
 +  * Giuseppe Casalicchio, Ludwig-Maximilians-Universität in Munich, Germany
 +  * Dawid Rymarczyk, Jagiellonian University, Poland
 +  * Jacek Tabor, Jagiellonian University, Poland
 +  * Bartosz Zieliński, Jagiellonian University, Poland
 +  * Abraham Duarte, Universidad Rey Juan Carlos I de Madrid, Spain
 +  * Sancho Salcedo Sanz, Universidad de Alcalá de Henares, Madrid, Spain
 +  * Benslimane Djamal, Lyon 1 University, France
 +  * Hujun Yin, University of Manchester, UK
 +  * Boyan Xu, Guangdong University of Technology, China
 +  * Cesar Analide, Universidad do Minho, Portugal
 +  * Maria Alcina Alpoim Sousa Pereira, Universidad do Minho, Portugal
 +  * Valery Naranjo, Universidad Politécnica de Valencia, Spain
 +  * Adrián Colomer, Universidad Politécnica de Valencia, Spain
  
  
Line 75: Line 125:
  
  
 +
 +===== Past events =====
 +  * [[praxai:start2021|PRAXAI 2021 @ DSAA2021]]
 +  * [[praxai:start2022|PRAXAI 2022 @ DSAA2022]]
  
praxai/start.1646903142.txt.gz · Last modified: 2022/03/10 09:05 by sbk
Driven by DokuWiki Recent changes RSS feed Valid CSS Valid XHTML 1.0