Knowledge & Data Engineering Systems

 

 

The Knowledge & Data Engineering Systems (KDES) research group is part of the Information, Data and Analysis (IDA) Section. KDES brings together the fundamental research areas of Distributed Computing, Knowledge Engineering, and Data Science.

KDES's strength lies in the spectrum of theoretical backgrounds and applications ranging from large-scale Distributed Computing and Information Systems, to Edge Computing , Distributed Machine Learning/AI, and Data-centric AI, focuses on building innovative distributed data science and engineering systems. 

Information, Data and Analysis Section

Data-centric AI

Distributed AI

Edge Computing

Data Management Systems

 

 

Research Topics

  • Distributed Data Management
  • Distributed AI & Federated Machine Learning & Reusability
  • Large-scale Data Analytics
  • Information Processing Systems

 

Research Projects & Materials

University of Glasgow cloisters

Academic Staff & Members

News & Events

  • 12 Nov

    Q Long's PhD Viva Success!

    Congratulations to Q Long for having his PhD Viva passed! Thesis title: 'Collaborative Distributed Machine Learning: From Knowledge Reuse to Sparsification in Federated Learning' (supervisors: Dr C Anagnostopoulos, Dr F Deligianni)
  • 09 Jun

    IEEE BigData 2024 Paper accepted!

    Our paper titled 'LIFE: Leader-driven Hierarchical & Inclusive Federated Learning' has been accepted for publication in IEEE BigData 2024, December 15-18, 2024, Washington DC, USA
  • 09 Jun

    IEEE TKDE 2024 Paper accepted!

    Our paper titled 'Task-Aware Data Selectivity in Pervasive Edge Computing Environments' has been accepted for publication in IEEE Transactions of Knowledge and Data Engineering (TKDE)
  • 09 Jun

    ECML PKDD 2024 Poster and Paper

    Join the presentation of our Federated Learning paper 'The Price of Labelling: A Two-Phase Federated Self-Learning Approach' authored by Aladwani, T., Anagnostopoulos, C. , Puthiya Parambath, S. and Deligianni, F in ECML/PKDD 2024!
  • 28 May

    IEEE DSAA 2024 Paper!

    Our Distributed AI paper 'CL-FML: Cluster-based & Label-aware Federated Meta-Learning for On-Demand Classification Tasks' authored by Aladwani, T., Anagnostopoulos, C. , Puthiya Parambath, S. and Deligianni, F has been accepted in the 1th IEEE International Conference on Data Science and Advanced Analytics (DSAA 2024), San Diego, CA, United States, 6-10 October 2024. Keywords: Federated Learning, Meta-Learning, Clustering, Data Augmentation.
Full News & Events listings