Call for Papers

The 2027 International Conference on the Intersection of Knowledge, Learning, and Reasoning (KLR 2027) provides a dedicated forum for researchers, practitioners, and industry experts to present their latest research and development at the methodological intersection of knowledge representation, machine learning, and automated reasoning. KLR 2027 will be held on February 26–28, 2027, in Zhengzhou, China. We cordially invite you to submit original, high-quality papers to the following tracks.

Track 1: Knowledge Representation, Reasoning, and Logic

Topics of interest:

  • Knowledge representation and reasoning

  • Logic and automated deduction

  • Knowledge graphs and applications

  • Constraint satisfaction and search

  • Uncertainty in reasoning

  • Web- and knowledge-based information systems

  • Ontology engineering

  • Query answering over knowledge bases

Track 2: Machine Learning, Data Mining, and Representation Learning

Topics of interest:

  • Deep learning and representation learning

  • Machine learning and data mining

  • Graph theory, graph mining, and graph neural networks

  • Image processing and analysis

  • Self-supervised and transfer learning

  • Knowledge discovery from structured and unstructured data

  • Evaluation and robustness of learned representations

Track 3: Knowledge-Driven Language and Agent Systems

Topics of interest:

  • Knowledge-enhanced natural language processing

  • Multi-agent systems and agent-based knowledge sharing

  • Language agents and tool use

  • Knowledge graphs in language understanding

  • Dialogue and conversational knowledge access

  • Agent communication and coordination

  • Knowledge-grounded generation

Track 4: Cognitive Learning and Uncertain Reasoning

Topics of interest:

  • Brain-inspired and neuromorphic learning

  • Implicit cognition and implicit learning

  • Uncertainty quantification and probabilistic reasoning

  • Cognitive modeling and computational neuroscience

  • Neuro-symbolic integration

  • Human-like learning and generalization

  • Reasoning under incomplete or noisy knowledge

  • For any questions, please contact the conference secretariat at contact_klr@163.com.