Meta-Knowledge Transfer/Communication in Different Systems
Workshop co-hosted at ECML/PKDD 2022.
Date: September 23rd, 2022 (14:30-18:30)
Location: ECML/PKDD Workshops and Tutorials, WTC in Room Kilimandjaro 3-4
This workshop is given as combined tutorial/workshop. Before the lunch, we will start with a tutorial on metalearning. The workshop will mostly be hosted live, in person (but it will be streamed for online participants).
Invited Speakers
- Timothy Hospedales, University of Edinburgh, Scotland
- Title: Meta-learning for Knowledge Transfer
- Pascal Hitzler, Kansas State University, USA
Program
14:30 - 14:35 Welcome and introduction by Henry Gouk
14:35 - 15:15 Keynote I by Timothy Hospedales: Meta-learning for Knowledge Transfer (Session Chair: Henry Gouk)
15:15 - 15:45 Poster Spotlight Presentations (Session Chair: Jan N. van Rijn)
15:45 - 17:00 Poster Session (1h15m, coffee arrives at 16:30)
17:00 - 17:45 Keynote II by Pascal Hitzler: Some advances regarding ontologies and neuro-symbolic artificial intelligence (Session Chair: Pavel Brazdil)
17:45 - 18:25 Panel Discussion. Panel Host: Henry Gouk. Confirmed Panelists: Marie Anastacio (RWTH Aachen University, Germany) Pascal Hitzler (Kansas State University, USA), Marco Loog (TU Delft, the Netherlands), Pavel Brazdil (University of Porto, Portugal).
18:25 - 18:30 Closing Remarks
We have noticed that there is a mix of participants onsite and online. We are currently investigating how we can best facilitate interaction between both audiences.
Proceedings
The workshop has proceedings hosted on PMLR, volume 191.
Organization
General organizers / Program Chairs
- Pavel Brazdil, University of Porto, Portugal
- Jan N. van Rijn, Leiden University, The Netherlands
- Henry Gouk, University of Edinburgh, Scotland
- Felix Mohr, Universidad de La Sabana, Colombia
Program Committee
- Salisu Abdulrahman (University of Kano, Nigeria)
- Annelot Bosman (Leiden University, the Netherlands)
- André de Carvalho (University of São Paulo, Brazil)
- Kemilly Dearo Garcia (Pegasystems, The Netherlands)
- Hugo Jair Escalante (INAOE LG Electronics AI Lab)
- Matthias Feurer (Albert-Ludwigs-Universitaet Freiburg, Germany)
- Eibe Frank (University of Waikato, NZ)
- João Gama (University of Porto, Portugal)
- Boyan Gao (University of Edinburgh, Scotland)
- Christophe Giraud-Carrier (Brigham Young University, USA)
- Rafael Gomes Mantovani (University of Paraná, Brazil)
- José Hernández-Orallo (Universitat Politecnica de Valencia, Spain)
- Mike Huisman (Leiden University, the Netherlands)
- Boyan Gao (University of Edinburgh, Portugal)
- Aaron Klein (Amazon AWS)
- Matthias König (Leiden University, Netherlands)
- Pavel Kordik (CVUT Prague, Czech Republik)
- Lars Kotthoff (University of Wyoming, Canada)
- Bernhard Pfahringer (Univ. of Waikato, NZ)
- Adriano Rivolli (UTFPR, Brazil)
- Kate Smith-Miles (University of Melbourne)
- Carlos Soares (University of Porto)
- Peter van der Putten (Leiden University, the Netherlands)
- Joaquin Vanschoren (Eindhoven Univ. of Technology)
- Martin Wistuba (Amazon Development Center Germany GmbH, Berlin)
Advisory Board
- Holger Hoos, RWTH Aachen University, Germany and Leiden University, the Netherlands
- Timothy Hospedales, University of Edinburgh, Scotland
- Frank Hutter, University of Freiburg, Germany
Call For Papers
Metaknowledge normally captures different aspects of existing (or potential) solutions, including, for instance which preprocessing methods should be used for the given data; which ML algorithms are relevant; which hyperparameters should be considered and how should these be set; how should all these elements be combined into useful pipelines or procedures. The aim of this workshop is to address the issues related to how (meta-)knowledge can be generated and transferred among different ML and AutoML systems, so that their joint capability to solve problems would be enhanced.
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 and meta-learning
- Explainable and interpretable meta-learning
Submission Format
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 can be made through Microsoft CMT
Format of the Workshop
The workshop will last a half a day, as it is forms part of a combined tutorial-workshop. It will include:
- Invited talks
- Short oral presentations
- Poster session
- Panel discussions on “Main challenges of communication of (meta)-knowledge among different systems”
Proceedings
The organizers are planning to prepare formal proceedings. The authors of accepted papers can decide whether they wish to have their full paper included or not. In the latter case, publication of short abstract would be possible.
Important Dates
- Paper submission deadline: June 27th, 2022 (extended)
- Paper acceptance notification: July 20th, 2022 (extended)
- Early registration deadline: July 22th, 2022
- Program and papers will be available online by: September 5th, 2022
- Workshop date: September 23rd, 2022 (afternoon)