The 1st International Workshop on
Knowledge Representation for Hybrid Intelligence
(KR4HI)
Amsterdam, The Netherlands
June 14th, 2022
Embedded Files
About
KR4HI is the first International Workshop on Knowledge Representation for Hybrid intelligence which will be co-located with the first international conference on Hybrid-Human Artificial Intelligence (HHAI 2022). The workshop will be held in Amsterdam (Vrije Universiteit Amsterdam) on June 14th, 2022.
Summary
As artificial intelligence (AI) technologies are playing more important roles in our daily lives than ever before, designing intelligent systems which can work with humans effectively (instead of replacing them) is becoming a central research theme, giving rise to hybrid intelligence (HI). HI stands for combining human and machine intelligence as a team in various scenarios, aiming to benefit from the complementary powers of both components in solving problems.
Developing such systems requires fundamentally novel solutions to major research problems in AI: current AI systems outperform humans in many cognitive tasks e.g., in pattern recognition or in playing video games, yet they fall short when it comes to tasks such as causal modelling, common sense reasoning, and behavioural human capabilities such as explaining its own decisions, adapting to different environments, adaptability to multiple contexts, collaborating with other human agents, etc. A particular challenge in developing such systems is to work with human input (high-level symbolic constraints or behavioural data).
Knowledge representation (KR) as a sub-discipline of AI, deals with representing background knowledge and reasoning with symbolic constraints. KR has a key potential for contributing to the development of HI systems, because it naturally brings human understanding and formal semantics (the understanding of machines) together. With this idea in mind, we welcome a wide array of works that use a KR formalism (or develop one) in an HI scenario. These works can range from purely theoretical to applied, or from purely symbolic to neural-symbolic ones, e.g., from “learning systems which take human demonstrations and symbolic constraints into account” to “explainable AI systems that generate symbolic explanations for humans” or can be in the context of socio-technical systems which hybrid intelligence naturally falls under.
Keynote Speakers
(University of Texas at Austin)
Title: Autonomous Systems in the Intersection of Reinforcement Learning, Controls, and Formal Methods
Ufuk Topcu is an Associate Professor in the Department of Aerospace Engineering and Engineering Mechanics at The University of Texas at Austin, where he holds the W. A. "Tex" Moncrief, Jr. Professorship in Computational Engineering and Sciences I. He is a core faculty member at the Oden Institute for Computational Engineering and Sciences and Texas Robotics and the director of the Autonomous Systems Group. Ufuk obtained his Doctor of Philosophy degree from the University of California, Berkeley in 2008. Prior to joining The University of Texas at Austin, he was with the Department of Electrical and Systems Engineering at the University of Pennsylvania. He was a postdoctoral scholar at the California Institute of Technology until 2012. Ufuk’s research focuses on the theoretical and algorithmic aspects of the design and verification of autonomous systems, typically in the intersection of formal methods, reinforcement learning, and control theory. He takes a relatively broad view on autonomy and tends to tackle abstract problems motivated by challenges cutting across multiple applications of autonomy. His research contributions have been recognised by the NSF CAREER Award, the Air Force Young Investigator Award, the IEEE CSS Antonio Ruberti Young Researcher Prize, and Oden Institute Distinguished Researcher Award. He is a member of the Computing Community Consortium Council.
(University of Groningen)
Title: Knowledge Representation for Hybrid Reasoning with Arguments and Evidence
Short Bio:
Bart Verheij's research focuses on the connections between knowledge, data and reasoning, as a contribution to responsible artificial intelligence. He uses an argumentation perspective, often with the law as domain of application. His teaching addresses the theory and design of knowledge and agent systems and computational argumentation. He studied pure mathematics at the University of Amsterdam and works at the University of Groningen in the Bernoulli Institute of Mathematics, Computer Science and Artificial Intelligence.
Theme of Submission
The workshop has an interdisciplinary theme and welcomes any work from any discipline which uses a KR formalism in a HI scenario. The relevant themes to be used in a HI scenario include but are not limited to:
• Argumentation Frameworks
• Integrating Learning and Reasoning (Neuro-Symbolic systems, Statistical Relational Learning)
• Formal or Applied Ontologies (Knowledge Graphs, Description Logics)
• Causal Inference/Counterfactual Reasoning
• Constraint Programming
• Epistemic Logics and Theory of Mind
• Formal Concept Analysis
• Automated Reasoning, Robotics and Planning
• Non-monotonic Reasoning (Answer-set Programming, Datalog)
• Models of uncertainty (Probabilistic Graphical models, Probabilistic/Fuzzy Logics)
• Temporal logics (Single-agent / Multiagent Logics)
• Preferential/Contextual Reasoning
Important Dates
Submission deadline: ̶A̶p̶r̶i̶l̶ ̶1̶4̶t̶h̶ May 1st, 2022 (AoE)
Notification of acceptance: June 2nd, 2022
Workshop date: June 14th, 2022
Submission Guidelines
Submission format: Submissions for contributing papers must be original (i.e., not submitted to any other venue) and are required to be in CEUR format (see http://ceur-ws.org/HOWTOSUBMIT.html) with 12 pages + references (incl. acknowledgements +supplementary material if necessary). Previously published articles or preliminary works can also be submitted in the form of extended abstracts (2 pages + references).
Submission link: Submissions are to be made via the EasyChair: https://easychair.org/conferences/?conf=kr4hi.
The review process: The review process will be carried out as single-blind.
Publication
Accepted papers will be published in CEUR workshop proceedings. Selected papers will be further invited for (extended version) submission to a special issue of the journal AI Communications.
Registration
Attendees (virtual or physical) should be registered via the website (https://www.hhai-conference.org/). The attendance fee is 100EUR for regular and 75 EUR for students. in case of applying for mini-scholarship for travel expenses, please contact Erman Acar (e.acar@liacs.leidenuniv.nl or erman.acar@vu.nl).
Event Location: VU Amsterdam, Main-building (Hoofdgebouw), Room: HG-02A36(31/15T)
Program Committee
Erman Acar (Leiden University & Vrije Universiteit Amsterdam, NL)
Vaishak Belle (University of Edinburgh, UK)
Thomas Bolander (Technical University of Denmark, DK)
Davide Grossi (University of Groningen, NL)
Ricardo Guimarães (University of Bergen, NO)
Loan Ho (Vrije Universiteit Amsterdam, NL)
Robert Loftin (TU Delft, NL)
Andrea Mazzullo (Free University of Bozen-Bolzano, IT)
Nicole Orzan (University of Groningen, NL)
Ana Ozaki (University of Bergen, NO)
Cosimo Persia (University of Bergen, NO)
Rafael Peñaloza (University of Milano-Bicocca, IT)
Nico Potyka (Imperial College London, UK)
Jandson S. Riberio (Fern Universität Hagen, DE)
Fernando Santos (University of Amsterdam, NL)
Andreas Sauter (Vrije Universiteit Amsterdam, NL)
Barış Sertkaya (Frankfurt University of Applied Sciences, DE)
Rieneke Verbrugge (University of Groningen, NL)
Frank van Harmelen (Vrije Universiteit Amsterdam, NL)
Ben Wright (Northeastern University, USA)
Organising Committee
Erman Acar (Leiden University & Vrije Universiteit Amsterdam)
Thomas Bolander (Technical University of Denmark)
Ana Ozaki (University of Bergen)
Rafael Peñaloza (University of Milano-Bicocca)
Contact
For any question, please contact Erman Acar via email: e.acar@liacs.leidenuniv.nl or erman.acar@vu.nl
https://docs.google.com/document/d/1b4e2Xt25bxmjL5-yE0YzSwAYNY6XBr3KQUz5PJ0hq3I/edit?usp=sharing
Page updated
Google Sites
Report abuse