Neuro-symbolic Metalearning and AutoML

Neuro-symbolic Metalearning and AutoML

Workshop co-hosted at ECML/PKDD 2023.

Date: September 18, 2023 (afternoon)

Location: Pending the ECML/PKDD room allocation

Invited Speakers

• Artur d’Avila Garcez, City University of London, UK
• Bernhard Pfahringer, University of Waikato, New Zealand

Organization

General organizers / Program Chairs (ordered by last name)

• Pavel Brazdil, University of Porto, Portugal
• Henry Gouk, University of Edinburgh, Scotland
• Jan N. van Rijn, Leiden University, The Netherlands
• Md Kamruzzaman Sarker, University of Hartford, USA

Call For Papers

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.

Main research areas:

• Controlling the learning processes
• Definitions of configuration spaces
• Few-shot learning
• Elaboration of feature hierarchies
• Exploiting hierarchy of features in learning
• Meta-learning
• Conditional meta-learning
• Meta-knowledge transfer
• Transfer learning
• Transfer of prior models
• Transfer of meta-knowledge between systems
• Symbolic vs subsymbolic meta-knowledge
• Neuro-symbolic learning
• Explainable and interpretable meta-learning
• Explainable artificial intelligence

Program Committee

• Shikha Bordia(Verisk Analytics)
• Kemilly Dearo
• Hugo Jair Escalante(INAOE)
• Eibe Frank (University of Waikato)
• Joao Gama (INESC TEC - LIAAD)
• Dagmar Gromann
• Filip Ilievski (USC/ISI)
• Pavel Kordík (Czech Technical University in Prague)
• Lars Kotthoff (University of Wyoming)
• Bo Liu (Auburn University)
• Robin Manhaeve (KU Leuven)
• Bernhard Pfahringer (University of Waikato)
• Peter van der Putten (Leiden University)
• Martin Wistuba (Amazon)

Submission

This workshop hosts two tracks:

• 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.
• 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.

Submissions go through the Conference Management Tool.

Please use the template suggested by the organisation of ECML/PKDD

Format of the Workshop

The workshop will last a half a day. It will include:

• Invited talks
• Short oral presentations
• Poster session
• Panel discussions on “Neuro-symbolic Metalearning and AutoML”

Proceedings

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.

Important Dates

• Workshop Paper Submission Deadline: 12 June 2023
• Workshop Paper Author Notification: 17 July 2023
• Camera Ready Deadline: End of July 2023
• Workshop: September 18, 2023 (afternoon)