<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<style type="text/css" style="display:none;"><!-- P {margin-top:0;margin-bottom:0;} --></style>
</head>
<body dir="ltr">
<div id="divtagdefaultwrapper" style="font-size:12pt;color:#000000;font-family:Calibri,Helvetica,sans-serif;" dir="ltr">
<p></p>
<div>******************************************</div>
<div>CFP Neuro-symbolic Metalearning and AutoML</div>
<div>Workshop co-hosted at ECML/PKDD 2023.</div>
<div>******************************************</div>
<div><br>
</div>
<div>Date: September 18, 2023 (afternoon)</div>
<div>Location: Pending the ECML/PKDD room allocation</div>
<div><br>
</div>
<div>Invited Speakers</div>
<div>* Artur d’Avila Garcez, City University of London, UK</div>
<div>* Other invited speakers soon to be confirmed.</div>
<div><br>
</div>
<div>Organization</div>
<div>General organizers / Program Chairs (ordered by last name)</div>
<div>Pavel Brazdil, University of Porto, Portugal</div>
<div>Henry Gouk, University of Edinburgh, Scotland</div>
<div>Jan N. van Rijn, Leiden University, The Netherlands</div>
<div>Md Kamruzzaman Sarker, University of Hartford, USA</div>
<div><br>
</div>
<div>Call For Papers</div>
<div>This workshop explores different types of meta-knowledge, such as performance summary statistics or pre-trained model weights. One way of acquiring meta-knowledge is by observing learning processes and representing it in such a way that it can be used
later to improve future learning processes. AutoML systems typically explore meta-knowledge acquired from a single task, e.g., by modelling the relationship between hyperparameters and model performance. Metalearning systems, on the other hand, normally explore
metaknowledge acquired on a collection of machine learning tasks. This can be used not only for selection of the best workflow(s) for the current task, but also for adaptation and fine-tuning of a prior model to the new task. Many current AutoML and metalearning
systems exploit both types of meta-knowledge. Neuro-symbolic systems explore the interplay between neural network-based learning and symbol-based learning to get the best of those two types of learning. While doing so, it tries to use the existing knowledge
as a concrete symbolic representation or as a transformed version of the symbolic representation suited for the learning algorithm. The goal of this workshop is to explore ways in which ideas can be cross-pollinated between the AutoML/Metalearning and neuro-symbolic
learning research communities. This could lead to, e.g., systems with interpretable meta-knowledge, and tighter integration between machine learning workflows and automated reasoning systems.</div>
<div><br>
</div>
<div>Main research areas:</div>
<div>Controlling the learning processes</div>
<div>Definitions of configuration spaces</div>
<div>Few-shot learning</div>
<div>Elaboration of feature hierarchies</div>
<div>Exploiting hierarchy of features in learning</div>
<div>Meta-learning</div>
<div>Conditional meta-learning</div>
<div>Meta-knowledge transfer</div>
<div>Transfer learning</div>
<div>Transfer of prior models</div>
<div>Transfer of meta-knowledge between systems</div>
<div>Symbolic vs subsymbolic meta-knowledge</div>
<div>Neuro-symbolic learning</div>
<div>Explainable and interpretable meta-learning</div>
<div>Explainable artificial intelligence</div>
<div><br>
</div>
<div>Important Dates</div>
<div>Workshop Paper Submission Deadline: 12 June 2023</div>
<div>Workshop Paper Author Notification: 17 July 2023</div>
<div>Camera Ready Deadline: End of July 2023</div>
<div>Workshop: September 18, 2023 (afternoon)</div>
<div><br>
</div>
<div>Submission</div>
<div>This workshop hosts two tracks:</div>
<div>* Original paper track: Authors can submit novel papers, that have not been accepted elsewhere. Please format your submission according to the LaTeX Lecture Notes in Computer Science format, maximal 12 pages.</div>
<div>* Poster of already published work: Authors can apply for a poster spot for a paper that has recently (less than 2 years) been published elsewhere. During submission, you send a link to the already published version of the work, and the peer-review will
determine whether it is a good match based on the topic.</div>
<div>Submissions go through the Conference Management Tool.</div>
<div><br>
</div>
<div>Format of the Workshop</div>
<div>The workshop will last a half a day. It will include:</div>
<div>* Invited talks</div>
<div>* Short oral presentations</div>
<div>* Poster session</div>
<div>* Panel discussions on “Neuro-symbolic Metalearning and AutoML”</div>
<div><br>
</div>
<div>Proceedings</div>
<div>Accepted papers can decide to opt-in to the formal workshop proceedings of ECML/PKDD 2023. The authors of accepted papers can decide whether they wish to have their full paper included or not. In the latter case, publication of a short abstract would be
possible.</div>
<div><br>
</div>
<br>
<p></p>
</div>
</body>
</html>