KR&ML@KR 2022

The last few years have witnessed a growing interest in AI methods that combine aspects of Machine Learning (ML) with insights and methods from the field of Knowledge Representation and Reasoning (KR). This trend is essentially motivated by the clear complementarity of ML and KR. For instance, the popularity and success of ML based systems has put issues such as explainability, bias and fairness firmly in the spotlight, and addressing these issues naturally leads to systems in which symbolic (or at least interpretable) representations play a more central role. On the other hand, ML also offers solutions for long-standing challenges in the field of KR, for instance related to efficient, noise-tolerant and ampliative inference, knowledge acquisition, and the limitations of symbolic representations. The synergy between ML and KR has the potential to lead to new advancements in fundamental AI challenges including, but not limited to, learning symbolic generalisations from raw (multi-modal) data, using knowledge to facilitate data-efficient learning, supporting interpretability of learned outcomes, federated multi-agent learning and decision making.

This year, for the third time, KR2022 will host a special session on "Knowledge Representation and Machine Learning", which aims at providing researchers and practitioners with a dedicated forum for the discussion of new ideas and research results at the intersection of these two fields. This special session will provide participants with the opportunity to make meaningful connections and develop a shared understanding of the challenges involved in developing innovative AI solutions that rely on a combination of insights and methods from ML and KR.

• Learning symbolic knowledge, such as ontologies and knowledge graphs, action theories, commonsense knowledge, spatial and temporal theories, preference models and causal models
• Logic-based, logical and relational learning algorithms
• Machine-learning driven reasoning algorithms
• Neural-symbolic learning
• Statistical relational learning
• Multi-agent learning
• Symbolic reinforcement learning
• Learning symbolic abstractions from unstructured data
• Explainable AI
• Expressive power of learning representations
• Knowledge-driven natural language understanding and dialogue
• Knowledge-driven decision making
• Knowledge-driven intelligent systems for internet of things and cybersecurity
• Architectures that combine data-driven techniques and formal reasoning