Connectionists: AIMLAI Workshop: Call for Papers (Extended deadline)

[Benoît Frenay]

AIMLAI at ECML/PKDD2024: Joint Tutorial on Explainable Models for Sequential Data and the International Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence



We invite researchers working on interpretability and explainability in ML/AI, and related topics, to submit regular (14 pages, single column) or short (7 pages, single column) papers to the AIMLAI workshop that will be held at ECML/PKDD 2024 in Vilnius. This year the workshop will feature a tutorial on explainable models for sequential data.



Website: https://project.inria.fr/aimlai/

Submission opening: May 2024

Submission deadline: June 15, 2024 June 28, 2024

Notification to authors: July 15, 2024 July 29, 2024



The purpose of AIMLAI (Advances in Interpretable Machine Learning and Artificial Intelligence) is to encourage principled research that will lead to the advancement of explainable, transparent, ethical and fair data mining, machine learning, and artificial intelligence. AIMLAI is a workshop that seeks top-quality submissions addressing uncovered important issues related to explainable and interpretable data mining and machine learning models. Papers should present novel research results in any of the topics of interest for the workshop as well as application experiences, tools and promising preliminary ideas. AIMLAI asks for contributions from researchers, academia, and industry working on topics addressing these challenges primarily from a technical point of view, but also

from a legal, ethical or sociological perspective. Besides the central topic of interpretable algorithms and explanation methods, we also welcome submissions that answer research questions like "how to measure and evaluate interpretability and explainability?" and "how to integrate humans in the machine learning pipeline for interpretability purposes?". This year’s edition of AIMLAI is open

to two kinds of submissions: regular papers (14 pages) and short papers (7 pages) in a single column format. A non-exhaustive list of topics that are of interest for AIMLAI are the following:



– Interpretable ML

• Interpretable-by-design models

• Explainable recommendation systems

• Multimodal explanations

• Explainability for large language models (LLMs)

• Mechanistic Interpretability

– Transparency in AI and ML

• Ethical aspects

• Legal aspects

• Fairness issues

– Methodology and formalization of interpretability and explainability

• Formal measures of interpretability/explainability

• Interpretability/complexity trade-offs

• How to evaluate interpretability

• User-centric interpretability

– Explanation modules

• Interpretability and Semantics: how to add semantics to explanations?

• Human-in-the-loop to construct and/or evaluate interpretable models

• Integration of ML algorithms, infovis and man-machine interfaces



The workshop will be a full-day event that will feature a half-day tutorial on explainable models for sequential data covering, among others, post-hoc explainability techniques on neural-based models, as well as the most recent techniques to extract explanations from large language models.



Submission Guidelines



Papers must be written in English and formatted according to the Springer LNCS guidelines. Regular papers must be 14 pages long maximum. Short papers are restricted to a maximum of 7 pages. In both cases the page limit excludes references, for which there is no limit. Overlength papers will be rejected without review (papers with smaller page margins and font sizes than specified in the

author instructions and set in the style files will also be treated as overlength). Authors who submit their work to AIMLAI 2024 commit themselves to present their paper at the workshop in case of acceptance. AIMLAI 2024 considers the author list submitted with the paper as final. No additions or deletions to this list may be made after paper submission, either during the review period, or in

case of acceptance, at the final camera ready stage. Condition for inclusion in the post-proceedings is that at least one of the co-authors has (in-person or virtually) presented the paper at the workshop.



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.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20240617/b5947f9d/attachment-0001.html>