TAILOR 2020: Workshop on the scientific foundations of Trustworthy AI, integrating learning, optimisation and reasoning University of Santiago de Compostela Santiago de Compostela, Spain, August 29-30, 2020 |
Conference website | https://liu.se/en/research/tailor |
Submission link | https://easychair.org/conferences/?conf=tailor2020 |
Abstract registration deadline | May 20, 2020 |
Submission deadline | May 20, 2020 |
The current scientific landscape is fragmented with many research groups working individually or in smaller constellations in often relatively isolated scientific communities: machine reasoning, machine learning, and optimization are examples of such mostly-disjoint communities.
The TAILOR workshop will bring these groups and researchers together in a unique atmosphere to discuss the state of the art and the latest advances in the integration of learning, optimisation and reasoning to provide the scientific foundations for Trustworthy AI.
The TAILOR community builds upon a large H2020 proposal on building a network of centers of excellence that includes over 100 labs in Europe.
Submission Guidelines
We welcome submissions to the workshop of the following types:
-
Presentations of relevant work that has recently been published or has already been accepted for publication in journals such as AIJ, JAIR, JMLR, MLJ, and major conferences such as AAAI, ICML, IJCAI, NeurIPS, SIGKDD, etc. The submission should in this case only consist of a copy of the accepted paper.
-
Long papers reporting on new material. Papers can be at most 16 pages in the Springer LNCS format. Please note that also shorter papers are welcome.
-
Extended abstracts that report on novel and preliminary ideas. Extended abstracts can be at most 6 pages in LNCS format.
-
Short position statements on the topic of the workshop, at most 6 pages in LNCS format.
The workshop is interested in foundational as well as more applied contributions. What matters is that they address the topics of the workshop - the integration of learning, optimisation and reasoning to provide the scientific foundations for Trustworthy AI.
Both long and short papers must be formatted according to LNCS guidelines (https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines) and submitted electronically through EasyChair: https://easychair.org/conferences/?conf=tailor2020
List of Topics
-
Trustworthiness: How to learn fair AI models, even in spite of biased data? How to develop explainable and interpretable AI decision processes? How to develop transparent AI systems and integrate them into the decision process for increasing user trust?
-
Learning, reasoning and optimisation: How to integrate AI paradigms and representations for reasoning, learning and optimisation in order to support trustworthy AI? Integrated approaches to learning, reasoning and optimisation should allow AI systems to bridge the gap between low-level perception and high-level reasoning, to combine knowledge-based and data-driven methods, to explain their behaviour and allow for introspection of the resulting models.
-
Deciding and Learning How to Act. How to empower an AI system with the ability of deliberating how to act in the world, reasoning on the effects of its actions, learning from past experiences, as well as monitoring the actual or simulated outcome of its actions, learning from possibly unexpected outcomes, and again reasoning and learning how to deal with such new outcome?
-
Reasoning and Learning in Social Contexts. Agents should not reason, learn and act in isolation. They will need to do it with others and among others. So, this topic is concerned with how AI systems should communicate, collaborate, negotiate and reach agreements with other AI and (eventually) human agents within a multi-agent system (MAS).
-
AutoAI: How to build AI tools, systems, and infrastructure that are performant, robust and trustworthy including having the ability to configure and tune itself for optimal performance? How can we support (1) people with limited AI expertise and (2) highly-skilled experts in building such AI systems?
Committees
Organizing committee
- Fredrik Heintz, Linköping University, Sweden (chair)
- Luc De Raedt, KU Leuven, Belgium
- Peter Flach, University of Bristol, UK
- Hector Geffner, ICREA and Universitat Pompeu Fabra, Spain
- Fosca Gianotti, National Research Council, Pisa, Italy
- Holger Hoos, Leiden University, The Netherlands
- Michela Milano, University of Bologna, Italy
- Barry O’Sullivan, University College Cork, Ireland
- Ana Paiva, University of Lisbon, Portugal
- Marc Schoenauer, INRIA, France
- Philipp Slusallek, DFKI, Germany
- Joaquin Vanschoren, Eindhoven University of Technology, The Netherlands
Publication
TAILOR 2020 proceedings will be published a Springer LNCS post proceedings.
Venue
The conference will be held at ECAI 2020, June 8-9, Santiago de Compostela, Spain.
Contact
All questions about submissions should be emailed to fredrik.heintz@liu.se.